Compare commits
16 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| b2521988e1 | |||
| dae123adac | |||
| 1c9ddbbea2 | |||
| 3f2782f5b7 | |||
| 865623ef3e | |||
| 4fdce3ca2c | |||
| c47881106e | |||
| 9a70f7378b | |||
| b18f608594 | |||
| d1f8a734c5 | |||
| 71041029e2 | |||
| 35018226ef | |||
| 8833a9c76b | |||
| 6c07409452 | |||
| 1c2541f7d6 | |||
| 9e25f18a3e |
+3
-2
@@ -16,6 +16,7 @@ import (
|
||||
"log"
|
||||
|
||||
"github.com/kami/maven/internal/loop"
|
||||
"github.com/kami/maven/internal/phraser"
|
||||
"github.com/kami/maven/internal/router"
|
||||
"github.com/kami/maven/internal/store"
|
||||
)
|
||||
@@ -35,10 +36,10 @@ func (h *reactiveHandler) resolveAck(ctx context.Context, text string, src turnS
|
||||
}
|
||||
if err := h.api.ResolveNudge(ctx, target.ID, store.NudgeActed, now); err != nil {
|
||||
log.Printf("voice: ack nudge %d (%s, %s): %v", target.ID, target.Rule, src, err)
|
||||
return "не получилось отметить.", true
|
||||
return phraser.Ack(phraser.FailAck, nil), true
|
||||
}
|
||||
log.Printf("voice: acked nudge %d (rule %s) from %s", target.ID, target.Rule, src)
|
||||
return "отлично, отметила.", true
|
||||
return phraser.Ack(phraser.AckNudge, nil), true
|
||||
}
|
||||
|
||||
// ackFromFact — post-action hook, called once the turn's decision has been
|
||||
|
||||
@@ -40,6 +40,7 @@ import (
|
||||
"context"
|
||||
"log"
|
||||
|
||||
"github.com/kami/maven/internal/phraser"
|
||||
"github.com/kami/maven/internal/router"
|
||||
)
|
||||
|
||||
@@ -58,10 +59,14 @@ func (h *reactiveHandler) actionChat(ctx context.Context, dec router.Decision) s
|
||||
// Conversational: build history from dialogue session (prior user turns)
|
||||
// and let the LLM respond from general knowledge + context.
|
||||
history := h.chatHistory()
|
||||
// The phraser hands back its own fallback text alongside the error, so the
|
||||
// turn survives a dead server and the failure still reaches the log.
|
||||
reply, err := h.phraser.PhraseChat(ctx, dec.Utterance, history)
|
||||
if err != nil {
|
||||
log.Printf("voice: chat: %v", err)
|
||||
return "поговорили."
|
||||
}
|
||||
if reply == "" {
|
||||
return phraser.ChatFallback()
|
||||
}
|
||||
return reply
|
||||
}
|
||||
|
||||
@@ -6,6 +6,7 @@ import (
|
||||
"strconv"
|
||||
|
||||
"github.com/kami/maven/internal/ipc"
|
||||
"github.com/kami/maven/internal/phraser"
|
||||
"github.com/kami/maven/internal/router"
|
||||
"github.com/kami/maven/internal/store"
|
||||
)
|
||||
@@ -14,7 +15,7 @@ import (
|
||||
// it for recall, and let pattern detection propose a routine.
|
||||
func (h *reactiveHandler) actionFact(ctx context.Context, dec router.Decision) string {
|
||||
if !dec.Slots.HasKey {
|
||||
return "не разобрала, что записать — попробуй иначе."
|
||||
return phraser.Ack(phraser.FailFactUnparsed, nil)
|
||||
}
|
||||
// A question is never a fact about him (#470). "какая последняя версия
|
||||
// языка Go?" used to land here, and the value stored was whatever the
|
||||
@@ -62,7 +63,7 @@ func (h *reactiveHandler) actionFact(ctx context.Context, dec router.Decision) s
|
||||
factID, err := h.api.WriteFact(ctx, req)
|
||||
if err != nil {
|
||||
log.Printf("voice: write fact: %v", err)
|
||||
return "не получилось сохранить факт."
|
||||
return phraser.Ack(phraser.FailFact, nil)
|
||||
}
|
||||
// Index the fact in long-term memory (best-effort, must not fail the fact
|
||||
// write). Facts aren't in the notes table, so this is the only recall path
|
||||
|
||||
@@ -5,6 +5,7 @@ import (
|
||||
"log"
|
||||
"strconv"
|
||||
|
||||
"github.com/kami/maven/internal/phraser"
|
||||
"github.com/kami/maven/internal/router"
|
||||
)
|
||||
|
||||
@@ -23,13 +24,13 @@ func (h *reactiveHandler) actionNote(ctx context.Context, dec router.Decision) s
|
||||
vec, err := router.EmbedPassage(ctx, h.embedder, dec.Utterance)
|
||||
if err != nil {
|
||||
log.Printf("voice: embed note: %v", err)
|
||||
return "не получилось сохранить заметку."
|
||||
return phraser.Ack(phraser.FailNote, nil)
|
||||
}
|
||||
noteTs := h.now()
|
||||
noteID, err := h.api.WriteNote(ctx, noteTs, dec.Utterance, vec, "tap:voice")
|
||||
if err != nil {
|
||||
log.Printf("voice: write note: %v", err)
|
||||
return "не получилось сохранить заметку."
|
||||
return phraser.Ack(phraser.FailNote, nil)
|
||||
}
|
||||
// Insert into long-term memory (best-effort, must not fail the note write).
|
||||
// text/ts in the meta make a Search hit self-describing (see bestRecall).
|
||||
|
||||
@@ -445,7 +445,13 @@ func (h *reactiveHandler) queryMemory(ctx context.Context, t *queryTurn) (string
|
||||
// A note is phrased in Maven's voice; a fact is read back as it was
|
||||
// stored.
|
||||
if hit.Meta["type"] == "note" {
|
||||
if reply, perr := h.phraser.PhraseQuery(ctx, t.dec.Utterance, []string{text}); perr == nil && reply != "" {
|
||||
reply, perr := h.phraser.PhraseQuery(ctx, t.dec.Utterance, []string{text})
|
||||
switch {
|
||||
case perr != nil:
|
||||
// Reading the note back verbatim beats the phraser's own fallback,
|
||||
// which only wraps the same text in "вот что я нашла:".
|
||||
log.Printf("voice: recall phrase: %v", perr)
|
||||
case reply != "":
|
||||
return reply, true
|
||||
}
|
||||
}
|
||||
@@ -792,7 +798,7 @@ func (h *reactiveHandler) queryGeneral(ctx context.Context, t *queryTurn) (strin
|
||||
reply, err := h.phraseWorld(ctx, t.dec.Utterance, nil)
|
||||
if errors.Is(err, phraser.ErrNoWorldModel) {
|
||||
log.Printf("voice: %q needs the world model and it is not available", t.dec.Utterance)
|
||||
return worldGap, true
|
||||
return worldGap(), true
|
||||
}
|
||||
if err != nil || reply == "" {
|
||||
return "не знаю.", true
|
||||
|
||||
@@ -4,6 +4,7 @@ import (
|
||||
"context"
|
||||
"log"
|
||||
|
||||
"github.com/kami/maven/internal/phraser"
|
||||
"github.com/kami/maven/internal/router"
|
||||
)
|
||||
|
||||
@@ -21,13 +22,13 @@ func (h *reactiveHandler) actionReminder(ctx context.Context, dec router.Decisio
|
||||
}
|
||||
}
|
||||
if !dec.Slots.HasTime {
|
||||
return "не получилось разобрать время напоминания."
|
||||
return phraser.Ack(phraser.FailReminderTime, nil)
|
||||
}
|
||||
}
|
||||
payload := `{"text":` + jsonString(dec.Utterance) + `}`
|
||||
if _, err := h.api.CreateReminder(ctx, dec.Slots.Time, payload, ""); err != nil {
|
||||
log.Printf("voice: create reminder: %v", err)
|
||||
return "не получилось поставить напоминание."
|
||||
return phraser.Ack(phraser.FailReminder, nil)
|
||||
}
|
||||
return ""
|
||||
}
|
||||
|
||||
@@ -5,6 +5,7 @@ import (
|
||||
"log"
|
||||
|
||||
"github.com/kami/maven/internal/ipc"
|
||||
"github.com/kami/maven/internal/phraser"
|
||||
"github.com/kami/maven/internal/router"
|
||||
"github.com/kami/maven/internal/store"
|
||||
"github.com/kami/maven/internal/tasks"
|
||||
@@ -40,18 +41,18 @@ func (h *reactiveHandler) captureTaskFromNote(ctx context.Context, dec router.De
|
||||
})
|
||||
if err != nil {
|
||||
log.Printf("voice: capture task: %v", err)
|
||||
return "не получилось записать задачу.", true
|
||||
return phraser.Ack(phraser.FailTask, nil), true
|
||||
}
|
||||
if resp.Promoted {
|
||||
// It was a candidate Maven derived from something she read, and he has
|
||||
// now said it himself. Saying "уже в списке" here would be answering a
|
||||
// confirmation with a shrug.
|
||||
return "поняла, беру в работу: " + cap.Text, true
|
||||
return phraser.Ack(phraser.AckTaskUrgent, map[string]string{"text": cap.Text}), true
|
||||
}
|
||||
if !resp.Created {
|
||||
return "это уже в списке.", true
|
||||
return phraser.Ack(phraser.AckTaskDuplicate, nil), true
|
||||
}
|
||||
return "записала: " + cap.Text, true
|
||||
return phraser.Ack(phraser.AckTask, map[string]string{"text": cap.Text}), true
|
||||
}
|
||||
|
||||
// queryTasks — "какие у меня задачи?", "что мне нужно сделать?".
|
||||
|
||||
@@ -8,6 +8,7 @@ import (
|
||||
"time"
|
||||
|
||||
"github.com/kami/maven/internal/ipc"
|
||||
"github.com/kami/maven/internal/phraser"
|
||||
"github.com/kami/maven/internal/router"
|
||||
)
|
||||
|
||||
@@ -108,7 +109,7 @@ func TestCaptureTaskFromNoteReportsStoreFailure(t *testing.T) {
|
||||
if !ok {
|
||||
t.Fatal("a failed capture still claims the turn — the note path must not double-write")
|
||||
}
|
||||
if !strings.Contains(reply, "не получилось") {
|
||||
if !phraser.IsAck(phraser.FailTask, nil, reply) {
|
||||
t.Errorf("reply = %q, want an honest failure", reply)
|
||||
}
|
||||
}
|
||||
|
||||
@@ -100,7 +100,7 @@ func (l llmCompleter) Complete(ctx context.Context, system, user string) (string
|
||||
// grammar, or a llama-server too old to honour one, gets the plain text it used
|
||||
// to get rather than an empty meeting summary.
|
||||
func unwrapSummary(raw string) string {
|
||||
s := stripThink(strings.TrimSpace(raw))
|
||||
s := phraser.StripThink(strings.TrimSpace(raw))
|
||||
start := strings.Index(s, "{")
|
||||
end := strings.LastIndex(s, "}")
|
||||
if start < 0 || end <= start {
|
||||
|
||||
@@ -121,8 +121,8 @@ func TestQueryRecallNoteCanWin(t *testing.T) {
|
||||
{text: "выучил пару аккордов", score: 0.50, kind: "note"},
|
||||
})
|
||||
reply := askQuery(t, h, q)
|
||||
if want := "вот что я нашла: молоко стоит в холодильнике"; reply != want {
|
||||
t.Errorf("reply %q, want %q", reply, want)
|
||||
if !phraser.IsSourcesFallback(reply, "молоко стоит в холодильнике") {
|
||||
t.Errorf("reply %q, want the note read back", reply)
|
||||
}
|
||||
// One text, the winning memory's — the answer came from the memory
|
||||
// pass, not from handing the phraser every note in the table.
|
||||
@@ -151,7 +151,7 @@ func TestQueryRecallNoteCanWin(t *testing.T) {
|
||||
{text: "молоко стоит в холодильнике", score: 0.860, kind: "note"},
|
||||
{text: "молоко закончилось", score: 0.858, kind: "note"},
|
||||
})
|
||||
if reply := askQuery(t, h, q); reply != "не знаю." {
|
||||
if reply := askQuery(t, h, q); !phraser.IsUnknownFallback(reply) {
|
||||
t.Errorf("reply %q, want silence", reply)
|
||||
}
|
||||
})
|
||||
|
||||
@@ -11,6 +11,7 @@ import (
|
||||
"unicode"
|
||||
|
||||
"github.com/kami/maven/internal/ipc"
|
||||
"github.com/kami/maven/internal/phraser"
|
||||
)
|
||||
|
||||
// resolveQuietToggle — pre-route keyword check. Returns (reply, true) when
|
||||
@@ -32,10 +33,10 @@ func (h *reactiveHandler) resolveQuietToggle(ctx context.Context, text string, s
|
||||
return "", false
|
||||
}
|
||||
val := "false"
|
||||
reply := "тихий режим выключен."
|
||||
reply := phraser.Ack(phraser.AckQuietOff, nil)
|
||||
if on {
|
||||
val = "true"
|
||||
reply = "тихий режим включён. буду реже напоминать."
|
||||
reply = phraser.Ack(phraser.AckQuietOn, nil)
|
||||
}
|
||||
if _, err := h.api.WriteFact(ctx, ipc.WriteFactReq{
|
||||
Ts: h.now(),
|
||||
@@ -46,7 +47,7 @@ func (h *reactiveHandler) resolveQuietToggle(ctx context.Context, text string, s
|
||||
Confidence: 1.0,
|
||||
}); err != nil {
|
||||
log.Printf("voice: write quiet_hours: %v", err)
|
||||
return "не получилось переключить тихий режим.", true
|
||||
return phraser.Ack(phraser.FailQuiet, nil), true
|
||||
}
|
||||
return reply, true
|
||||
}
|
||||
|
||||
+11
-100
@@ -2,122 +2,33 @@ package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"encoding/json"
|
||||
"strings"
|
||||
"time"
|
||||
|
||||
"github.com/kami/maven/internal/llm"
|
||||
"github.com/kami/maven/internal/persona"
|
||||
"github.com/kami/maven/internal/phraser"
|
||||
"github.com/kami/maven/internal/router"
|
||||
"github.com/kami/maven/internal/voice"
|
||||
)
|
||||
|
||||
// completer is the LLM seam for the replier (subset of router.Completer).
|
||||
// *llm.Client satisfies it.
|
||||
type completer interface {
|
||||
Complete(ctx context.Context, r llm.Req) (string, error)
|
||||
}
|
||||
|
||||
// llmReplier phrases reactive confirmations with the resident model
|
||||
// (Qwen3-1.7B). Stub is the
|
||||
// floor on any error (offline-safe). Maven speaks as "she", feminine RU.
|
||||
// llmReplier is the daemon-side wiring around phraser.Replier: it owns the
|
||||
// deterministic floor, and nothing else. The phrasing itself, the prompt and the
|
||||
// output parsing live in internal/phraser so the eval can score them (#396).
|
||||
type llmReplier struct {
|
||||
c completer
|
||||
p *phraser.Replier
|
||||
stub *voice.StubReplier
|
||||
|
||||
// block renders the shared context block per turn (who he is, the time).
|
||||
// nil ⇒ the prompt stands alone.
|
||||
block func() string
|
||||
}
|
||||
|
||||
func newLLMReplier(c completer, block func() string) *llmReplier {
|
||||
return &llmReplier{c: c, stub: voice.NewStubReplier(), block: block}
|
||||
func newLLMReplier(c phraser.Completer, block func() string) *llmReplier {
|
||||
return &llmReplier{p: phraser.NewReplier(c, block), stub: voice.NewStubReplier()}
|
||||
}
|
||||
|
||||
const replySystem = `Ты — Maven, домашняя ассистентка (о себе — в женском роде). Владелец — мужчина, говоришь с ним на "ты", в единственном числе; никогда не "вы"/"ваш" и не "он"/"его". Подтверди действие РОВНО ОДНИМ коротким предложением (≤120 символов), по-русски, спокойно и без официальных формулировок. Не задавай вопросов, не повторяй слова, не добавляй ничего после точки. Отвечай ТОЛЬКО одним объектом JSON с полями "response" (текст) и "mood" (ровно одно из: neutral, happy, thinking, tired, confused).
|
||||
Пример: {"response": "Записала, что ты выпил стакан воды.", "mood": "neutral"}
|
||||
Никогда не пиши "..." в поле response.`
|
||||
|
||||
// Reply never fails: a clarify, a model error and an unusable generation all
|
||||
// answer from the stub, which is what keeps a turn from breaking on the model.
|
||||
func (r *llmReplier) Reply(d router.Decision) string {
|
||||
if d.Clarify {
|
||||
return r.stub.Reply(d)
|
||||
}
|
||||
ctx, cancel := context.WithTimeout(context.Background(), 60*time.Second)
|
||||
defer cancel()
|
||||
out, err := r.c.Complete(ctx, llm.Req{
|
||||
System: persona.Prepend(r.block, replySystem),
|
||||
User: replyContext(d),
|
||||
Grammar: phraser.ResponseGrammar,
|
||||
MaxTokens: 512,
|
||||
RepeatPenalty: 1.3,
|
||||
})
|
||||
if err != nil {
|
||||
out, err := r.p.PhraseReply(context.Background(), d)
|
||||
if err != nil || out == "" {
|
||||
return r.stub.Reply(d)
|
||||
}
|
||||
out = stripThink(out)
|
||||
if response, _ := parseResponseMood(out); response != "" {
|
||||
return response
|
||||
}
|
||||
// fallback: try plain-text parsing
|
||||
if out = firstSentence(out); out != "" {
|
||||
return out
|
||||
}
|
||||
return r.stub.Reply(d)
|
||||
}
|
||||
|
||||
// firstSentence trims the model's output to a single clean confirmation: first
|
||||
// line, first sentence, whitespace-normalized — the last-line defense against a
|
||||
// small model that rambles past the first period despite the prompt + stop.
|
||||
// stripThink removes the <think> block that Thinking-variant models emit.
|
||||
func stripThink(s string) string {
|
||||
if i := strings.LastIndex(s, "</think>"); i >= 0 {
|
||||
s = strings.TrimSpace(s[i+8:])
|
||||
}
|
||||
return s
|
||||
}
|
||||
|
||||
func firstSentence(s string) string {
|
||||
s = strings.TrimSpace(s)
|
||||
if i := strings.IndexByte(s, '\n'); i >= 0 {
|
||||
s = s[:i]
|
||||
}
|
||||
// keep up to and including the first sentence-ending punctuation.
|
||||
if i := strings.IndexAny(s, ".!?"); i >= 0 {
|
||||
s = s[:i+1]
|
||||
}
|
||||
return strings.TrimSpace(s)
|
||||
}
|
||||
|
||||
// parseResponseMood extracts {"response","mood"} from LLM output, tolerant
|
||||
// of thinking tokens and extra text before/after the JSON block.
|
||||
func parseResponseMood(raw string) (response, mood string) {
|
||||
cleaned := strings.TrimSpace(raw)
|
||||
start := strings.Index(cleaned, "{")
|
||||
end := strings.LastIndex(cleaned, "}")
|
||||
if start < 0 || end < 0 || end <= start {
|
||||
return "", ""
|
||||
}
|
||||
var parsed struct {
|
||||
Response string `json:"response"`
|
||||
Mood string `json:"mood"`
|
||||
}
|
||||
if err := json.Unmarshal([]byte(cleaned[start:end+1]), &parsed); err != nil {
|
||||
return "", ""
|
||||
}
|
||||
return parsed.Response, parsed.Mood
|
||||
}
|
||||
|
||||
// replyContext renders the decision into a compact RU description for the model.
|
||||
func replyContext(d router.Decision) string {
|
||||
switch d.Intent {
|
||||
case router.IntentFact:
|
||||
return "записала факт: " + d.Slots.Key + " " + d.Slots.Value
|
||||
case router.IntentNote:
|
||||
return "сохранила заметку: " + d.Slots.Text
|
||||
case router.IntentReminder:
|
||||
return "поставила напоминание: " + d.Slots.Text
|
||||
default:
|
||||
return string(d.Intent) + ": " + d.Slots.Text
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
@@ -10,23 +10,18 @@ import (
|
||||
"github.com/kami/maven/internal/voice"
|
||||
)
|
||||
|
||||
type mockCompleter struct {
|
||||
// The phrasing itself is tested in internal/phraser. What is left here is the
|
||||
// only thing the daemon adds: the stub floor, on the three ways a reply can
|
||||
// fail to arrive.
|
||||
type stubCompleter struct {
|
||||
out string
|
||||
err error
|
||||
}
|
||||
|
||||
func (m mockCompleter) Complete(_ context.Context, _ llm.Req) (string, error) { return m.out, m.err }
|
||||
func (s stubCompleter) Complete(_ context.Context, _ llm.Req) (string, error) { return s.out, s.err }
|
||||
|
||||
func TestLLMReplierReturnsLLMReply(t *testing.T) {
|
||||
r := newLLMReplier(mockCompleter{out: `{"response":"записала, кофе закончился","mood":"neutral"}`}, nil)
|
||||
got := r.Reply(router.Decision{Intent: router.IntentNote, Slots: router.Slots{Text: "кофе закончился"}})
|
||||
if got != "записала, кофе закончился" {
|
||||
t.Errorf("got %q, want %q", got, "записала, кофе закончился")
|
||||
}
|
||||
}
|
||||
|
||||
func TestLLMReplierFallsBackToPlainText(t *testing.T) {
|
||||
r := newLLMReplier(mockCompleter{out: "записала, кофе закончился"}, nil)
|
||||
func TestLLMReplierPassesTheModelReplyThrough(t *testing.T) {
|
||||
r := newLLMReplier(stubCompleter{out: `{"response":"записала, кофе закончился","mood":"neutral"}`}, nil)
|
||||
got := r.Reply(router.Decision{Intent: router.IntentNote, Slots: router.Slots{Text: "кофе закончился"}})
|
||||
if got != "записала, кофе закончился" {
|
||||
t.Errorf("got %q, want %q", got, "записала, кофе закончился")
|
||||
@@ -34,54 +29,40 @@ func TestLLMReplierFallsBackToPlainText(t *testing.T) {
|
||||
}
|
||||
|
||||
func TestLLMReplierFallsBackToStubOnError(t *testing.T) {
|
||||
r := newLLMReplier(mockCompleter{err: errTestLLMDown}, nil)
|
||||
noteDec := router.Decision{Intent: router.IntentNote}
|
||||
got := r.Reply(noteDec)
|
||||
want := voice.NewStubReplier().Reply(noteDec)
|
||||
if got != want {
|
||||
t.Errorf("on llm error: got %q, want stub %q", got, want)
|
||||
}
|
||||
r := newLLMReplier(stubCompleter{err: errReplierTest}, nil)
|
||||
assertAck(t, r, router.Decision{Intent: router.IntentNote}, phraser.AckNote, "llm error")
|
||||
}
|
||||
|
||||
func TestLLMReplierFallsBackToStubOnEmpty(t *testing.T) {
|
||||
r := newLLMReplier(mockCompleter{out: ""}, nil)
|
||||
noteDec := router.Decision{Intent: router.IntentNote}
|
||||
got := r.Reply(noteDec)
|
||||
want := voice.NewStubReplier().Reply(noteDec)
|
||||
if got != want {
|
||||
t.Errorf("on empty llm: got %q, want stub %q", got, want)
|
||||
}
|
||||
r := newLLMReplier(stubCompleter{out: ""}, nil)
|
||||
assertAck(t, r, router.Decision{Intent: router.IntentNote}, phraser.AckNote, "empty llm")
|
||||
}
|
||||
|
||||
func TestLLMReplierClarifyUsesStub(t *testing.T) {
|
||||
r := newLLMReplier(mockCompleter{out: "я всё поняла"}, nil)
|
||||
clarifyDec := router.Decision{Clarify: true}
|
||||
got := r.Reply(clarifyDec)
|
||||
want := voice.NewStubReplier().Reply(clarifyDec)
|
||||
if got != want {
|
||||
t.Errorf("on clarify: got %q, want stub %q", got, want)
|
||||
r := newLLMReplier(stubCompleter{out: "я всё поняла"}, nil)
|
||||
assertStub(t, r, router.Decision{Clarify: true}, "clarify")
|
||||
}
|
||||
|
||||
// assertAck — the stub picks between variants now, so two calls to it are not
|
||||
// expected to match. What must hold is that the reply is a line that entry can
|
||||
// produce, which is the same claim without pinning one wording.
|
||||
func assertAck(t *testing.T, r *llmReplier, d router.Decision, key, what string) {
|
||||
t.Helper()
|
||||
if got := r.Reply(d); !phraser.IsAck(key, nil, got) {
|
||||
t.Errorf("on %s: got %q, want a %q line", what, got, key)
|
||||
}
|
||||
}
|
||||
|
||||
var errTestLLMDown = errTest("llm down")
|
||||
func assertStub(t *testing.T, r *llmReplier, d router.Decision, what string) {
|
||||
t.Helper()
|
||||
got, want := r.Reply(d), voice.NewStubReplier().Reply(d)
|
||||
if got != want {
|
||||
t.Errorf("on %s: got %q, want stub %q", what, got, want)
|
||||
}
|
||||
}
|
||||
|
||||
var errReplierTest = errTest("llm down")
|
||||
|
||||
type errTest string
|
||||
|
||||
func (e errTest) Error() string { return string(e) }
|
||||
|
||||
// grammarRecorder captures the request so the grammar can be asserted on.
|
||||
type grammarRecorder struct{ req llm.Req }
|
||||
|
||||
func (g *grammarRecorder) Complete(_ context.Context, r llm.Req) (string, error) {
|
||||
g.req = r
|
||||
return `{"response":"записала","mood":"neutral"}`, nil
|
||||
}
|
||||
|
||||
func TestLLMReplierCarriesTheResponseGrammar(t *testing.T) {
|
||||
rec := &grammarRecorder{}
|
||||
r := newLLMReplier(rec, nil)
|
||||
r.Reply(router.Decision{Intent: router.IntentNote, Slots: router.Slots{Text: "кофе закончился"}})
|
||||
if rec.req.Grammar != phraser.ResponseGrammar {
|
||||
t.Errorf("grammar = %q, want phraser.ResponseGrammar", rec.req.Grammar)
|
||||
}
|
||||
}
|
||||
|
||||
@@ -11,6 +11,7 @@ import (
|
||||
"time"
|
||||
|
||||
"github.com/kami/maven/internal/ipc"
|
||||
"github.com/kami/maven/internal/phraser"
|
||||
"github.com/kami/maven/internal/store"
|
||||
)
|
||||
|
||||
@@ -51,10 +52,10 @@ func (h *reactiveHandler) resolveSnooze(ctx context.Context, text string, src tu
|
||||
}
|
||||
if err := h.api.ResolveNudge(ctx, target.ID, store.NudgeSnoozed, now); err != nil {
|
||||
log.Printf("voice: snooze nudge %d (%s, %s): %v", target.ID, target.Rule, src, err)
|
||||
return "не получилось отложить.", true
|
||||
return phraser.Ack(phraser.FailSnooze, nil), true
|
||||
}
|
||||
log.Printf("voice: snoozed nudge %d (rule %s) from %s", target.ID, target.Rule, src)
|
||||
return "хорошо, вернусь к этому позже.", true
|
||||
return phraser.Ack(phraser.AckSnooze, nil), true
|
||||
}
|
||||
|
||||
// pendingNudge — the newest still-pending nudge sent inside snoozeWindow.
|
||||
|
||||
@@ -23,7 +23,11 @@ type worldPhraser interface {
|
||||
// question about his meeting came back as a swimming competition in Nottingham.
|
||||
// Naming the gap is the rule CLAUDE.md already applies to a sibling service
|
||||
// being down.
|
||||
const worldGap = "сейчас не могу ответить — большая модель недоступна, а придумывать не хочу."
|
||||
//
|
||||
// The wording lives in fallbacks_ru_v1.json and is fixed there, not picked from
|
||||
// variants: this sentence names one specific gap and must not drift into a
|
||||
// general "I don't know".
|
||||
func worldGap() string { return phraser.WorldGap() }
|
||||
|
||||
// phraseWorld asks the world model, or reports the gap.
|
||||
//
|
||||
@@ -54,7 +58,11 @@ func (h *reactiveHandler) phraseSource(ctx context.Context, name, utterance stri
|
||||
log.Printf("voice: %s: no world model, reading the source back instead", name)
|
||||
return ""
|
||||
case err != nil:
|
||||
// The resident phraser answers this call with its fallback text and the
|
||||
// error together. Drop the text: these callers hold the passage itself
|
||||
// and read it back better than "вот что я нашла: <passage>" does.
|
||||
log.Printf("voice: %s: phrase: %v", name, err)
|
||||
return ""
|
||||
}
|
||||
return reply
|
||||
}
|
||||
|
||||
@@ -35,7 +35,7 @@ func TestQueryGeneralNamesTheGap(t *testing.T) {
|
||||
if !ok {
|
||||
t.Fatal("queryGeneral passed on the last source in the chain")
|
||||
}
|
||||
if reply != worldGap {
|
||||
if reply != worldGap() {
|
||||
t.Fatalf("reply = %q, want the named gap", reply)
|
||||
}
|
||||
if g.worldCalls != 1 {
|
||||
@@ -51,7 +51,7 @@ func TestQueryGeneralWithoutAWorldModelIsUnchanged(t *testing.T) {
|
||||
if !ok {
|
||||
t.Fatal("queryGeneral passed on the last source in the chain")
|
||||
}
|
||||
if reply != "не знаю." {
|
||||
if !phraser.IsUnknownFallback(reply) {
|
||||
t.Fatalf("reply = %q, want the Stub's answer", reply)
|
||||
}
|
||||
}
|
||||
@@ -61,12 +61,12 @@ func TestQueryGeneralWithoutAWorldModelIsUnchanged(t *testing.T) {
|
||||
// English in it.
|
||||
func TestWorldGapIsInPersona(t *testing.T) {
|
||||
for _, bad := range []string{"вы", "ваш", "рад ", "дорогой", "милый"} {
|
||||
if strings.Contains(worldGap, bad) {
|
||||
t.Errorf("the gap phrase contains %q: %s", bad, worldGap)
|
||||
if strings.Contains(worldGap(), bad) {
|
||||
t.Errorf("the gap phrase contains %q: %s", bad, worldGap())
|
||||
}
|
||||
}
|
||||
if strings.ContainsAny(worldGap, "abcdefghijklmnopqrstuvwxyz") {
|
||||
t.Errorf("the gap phrase has Latin letters in it: %s", worldGap)
|
||||
if strings.ContainsAny(worldGap(), "abcdefghijklmnopqrstuvwxyz") {
|
||||
t.Errorf("the gap phrase has Latin letters in it: %s", worldGap())
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@@ -0,0 +1,65 @@
|
||||
# Recall topic veto, what it costs and what it buys, 2026-08-03
|
||||
|
||||
Vikunja #496. The task asked for a cross-language fix. Skip the topic veto in
|
||||
`memory.RecallAllowed` when the question and the hit are in different scripts.
|
||||
An English question would then stop losing a Russian note.
|
||||
|
||||
No such case exists. No fixture case puts the question and its wanted note in
|
||||
different scripts. The case the task named is not one either.
|
||||
|
||||
en-hard-024
|
||||
query "what fixed the screen problem"
|
||||
note "the flicker went away once i swapped the display cable"
|
||||
|
||||
Both are English. It is a paraphrase failure, not a language failure. A script
|
||||
test would not have changed a single case, and neither would a bilingual stem
|
||||
map.
|
||||
|
||||
## What the veto is worth today
|
||||
|
||||
Measured with the real embedder, multilingual-e5-small int8, gate 0.55, margin
|
||||
0.008. The first row is the veto as it ships. The second is `RecallAllowed`
|
||||
forced to true.
|
||||
|
||||
| | cases passing | answered | false recall | silenced by gate |
|
||||
|---|---|---|---|---|
|
||||
| veto on | 22/32 | 17/27 | 0/5 | 2 |
|
||||
| veto off | 22/32 | 18/27 | 1/5 | 1 |
|
||||
|
||||
The pass count does not move. The veto trades one true recall for one false one.
|
||||
It costs `en-hard-024` and it buys `ru-silent-029`:
|
||||
|
||||
ru-silent-029
|
||||
query "во сколько отходит поезд"
|
||||
note "погулял вдоль реки" 0.835, margin 0.019
|
||||
|
||||
The second case counted as silenced by the gate is `ru-home-026` at margin
|
||||
0.001, which the margin gate stops. The veto has nothing to do with it.
|
||||
|
||||
## Why no lexical rule separates the two
|
||||
|
||||
`en-hard-024` and `ru-silent-029` are in the same lexical class. Both questions
|
||||
share zero content words with their hit, and neither carries a first-person
|
||||
marker. The scores sit on top of each other, 0.826 against 0.835, and so do the
|
||||
margins, 0.023 against 0.019. Only one thing separates them. A screen problem
|
||||
and a swapped display cable are the same event. A train and a river walk are
|
||||
not. The embedder scores that difference at nine thousandths.
|
||||
|
||||
So the signal is semantic and the gate is lexical. Any rule cheap enough to sit
|
||||
in `RecallAllowed` and strong enough to recover `en-hard-024` also re-admits
|
||||
`ru-silent-029`, which puts false recall back to 1/5.
|
||||
|
||||
One near-miss rule was tried on paper and rejected: let the veto pass when the
|
||||
hit itself is first person. It works on these two, because the English note says
|
||||
"i swapped" and the Russian note says only "погулял". It is backwards as a
|
||||
principle. A first-person note is exactly the personal note the veto keeps away
|
||||
from a world question. The rule would weaken the veto where it was designed to
|
||||
bite. It survives here only because Russian drops the pronoun.
|
||||
|
||||
## Decision
|
||||
|
||||
Accept the loss. `en-hard-024` stays silenced and false recall stays 0/5.
|
||||
|
||||
The way out is a reranker, not a longer word list. Recall@3 is 85.2% against
|
||||
recall@1 at 70.4%, so the right note is usually in the returned set and ranked
|
||||
wrong. That is where the remaining points are, and it is not this task.
|
||||
@@ -60,6 +60,14 @@ var firstPerson = map[string]bool{
|
||||
// kill one false one. A question about his own life keeps the embedder alone
|
||||
// as its judge. A question about the world has to name something the memory
|
||||
// actually mentions.
|
||||
//
|
||||
// The veto's price was re-measured on 2026-08-03 (#496,
|
||||
// docs/evals/2026-08-03-recall-topic-veto.md). It costs one true recall and
|
||||
// buys one false one, and the fixture pass count is the same either way. The
|
||||
// lost case is an English paraphrase, not the cross-language loss it was
|
||||
// reported as, and the fixture has no cross-language case at all. Do not add a
|
||||
// script test or a bilingual stem map for it — both are no-ops here. The
|
||||
// separating signal is semantic and belongs in a reranker, not in this file.
|
||||
func RecallAllowed(query, text string) bool {
|
||||
if mentionsHim(query) {
|
||||
return true
|
||||
|
||||
@@ -31,6 +31,22 @@ func TestRecallAllowed(t *testing.T) {
|
||||
}
|
||||
}
|
||||
|
||||
// The known cost of the veto and the thing that pays for it, both measured on
|
||||
// the held-out fixture with the real embedder (#496,
|
||||
// docs/evals/2026-08-03-recall-topic-veto.md). The two are one lexical class:
|
||||
// zero shared content words, no first-person marker, scores 0.826 against 0.835
|
||||
// and margins 0.023 against 0.019. Recovering the first re-admits the second,
|
||||
// which puts false recall back to 1/5. Anyone loosening the veto has to move
|
||||
// the first line without moving the second.
|
||||
func TestRecallVetoTradeIsPinned(t *testing.T) {
|
||||
if RecallAllowed("what fixed the screen problem", "the flicker went away once i swapped the display cable") {
|
||||
t.Error("en-hard-024 is expected to stay vetoed — if this passes now, re-measure false recall before celebrating")
|
||||
}
|
||||
if RecallAllowed("во сколько отходит поезд", "погулял вдоль реки") {
|
||||
t.Error("ru-silent-029 must stay vetoed — this is the false recall the veto exists to stop")
|
||||
}
|
||||
}
|
||||
|
||||
// A question made only of filler has no topic word to match on, and the score
|
||||
// gate is then the only judge it can have.
|
||||
func TestRecallAllowedFallsBackWhenNothingToCompare(t *testing.T) {
|
||||
|
||||
@@ -0,0 +1,84 @@
|
||||
{
|
||||
"schema_version": 1,
|
||||
"name": "russian capture acknowledgements v1",
|
||||
"notes": [
|
||||
"What she says after storing something he said, and what she says when storing it failed. 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 он/его about him. No pet names.",
|
||||
"He hears these many times a day, so most entries carry variants: identical wording is what makes a confirmation stop registering as one.",
|
||||
"Placeholders: {key} {value} the fact he stated, {fn} the action, {text} the task title. His data is interpolated Go-side — the file holds the frame, never his words.",
|
||||
"An acknowledgement confirms and stops. It does not ask a follow-up question and it does not editorialise about what he stored."
|
||||
],
|
||||
"entries": {
|
||||
"ack_fact": {
|
||||
"variants": ["записала факт.", "записала.", "запомнила."]
|
||||
},
|
||||
"ack_fact_key": {
|
||||
"variants": ["отметила: {key}", "записала: {key}", "запомнила: {key}"]
|
||||
},
|
||||
"ack_fact_kv": {
|
||||
"variants": ["отметила: {key} = {value}", "записала: {key} — {value}", "запомнила: {key} — {value}"]
|
||||
},
|
||||
"ack_note": {
|
||||
"variants": ["сохранила заметку.", "заметка сохранена.", "записала в заметки."]
|
||||
},
|
||||
"ack_reminder": {
|
||||
"variants": ["напомню.", "напомню, не забуду.", "хорошо, напомню."]
|
||||
},
|
||||
"ack_act": {
|
||||
"variants": ["ок, записала действие: {fn}", "приняла действие: {fn}"]
|
||||
},
|
||||
"ack_task": {
|
||||
"variants": ["записала: {text}", "добавила в задачи: {text}", "внесла в список: {text}"]
|
||||
},
|
||||
"ack_task_urgent": {
|
||||
"variants": ["поняла, беру в работу: {text}", "поняла, это срочно: {text}"]
|
||||
},
|
||||
"ack_task_duplicate": {
|
||||
"variants": ["это уже в списке.", "такое уже есть в задачах."]
|
||||
},
|
||||
"ack_nudge": {
|
||||
"variants": ["отлично, отметила.", "отметила.", "хорошо, отметила."]
|
||||
},
|
||||
"ack_snooze": {
|
||||
"variants": ["хорошо, вернусь к этому позже.", "ладно, напомню попозже.", "хорошо, отложила."]
|
||||
},
|
||||
"ack_generic": {
|
||||
"variants": ["приняла.", "поняла."]
|
||||
},
|
||||
"quiet_on": {
|
||||
"fixed": true,
|
||||
"variants": ["тихий режим включён. буду реже напоминать."]
|
||||
},
|
||||
"quiet_off": {
|
||||
"fixed": true,
|
||||
"variants": ["тихий режим выключен."]
|
||||
},
|
||||
"fail_fact": {
|
||||
"variants": ["не получилось сохранить факт.", "факт не сохранился."]
|
||||
},
|
||||
"fail_note": {
|
||||
"variants": ["не получилось сохранить заметку.", "заметка не сохранилась."]
|
||||
},
|
||||
"fail_reminder": {
|
||||
"variants": ["не получилось поставить напоминание.", "напоминание не поставилось."]
|
||||
},
|
||||
"fail_reminder_time": {
|
||||
"variants": ["не получилось разобрать время напоминания.", "не поняла, на когда напомнить."]
|
||||
},
|
||||
"fail_task": {
|
||||
"variants": ["не получилось записать задачу.", "задача не записалась."]
|
||||
},
|
||||
"fail_ack": {
|
||||
"variants": ["не получилось отметить.", "не смогла отметить."]
|
||||
},
|
||||
"fail_snooze": {
|
||||
"variants": ["не получилось отложить.", "не смогла отложить."]
|
||||
},
|
||||
"fail_quiet": {
|
||||
"variants": ["не получилось переключить тихий режим.", "тихий режим не переключился."]
|
||||
},
|
||||
"fail_fact_unparsed": {
|
||||
"variants": ["не разобрала, что записать — попробуй иначе.", "не поняла, что записать. скажи иначе?"]
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,162 @@
|
||||
package phraser
|
||||
|
||||
// The capture acknowledgements — what she says after storing something he said,
|
||||
// and what she says when storing it failed.
|
||||
//
|
||||
// They were string literals in eight files under cmd/mavend plus the stub
|
||||
// replier in internal/voice. He hears them many times a day, which is exactly
|
||||
// why they need variants and exactly why rewording one must not be a rebuild.
|
||||
// Same shape as fallbacks_ru_v1.json, on the shared deck (deck.go).
|
||||
//
|
||||
// His data stays Go-side. The file holds "отметила: {key} = {value}"; the key
|
||||
// and the value are interpolated here, so nothing he said lives in the copy.
|
||||
|
||||
import (
|
||||
_ "embed"
|
||||
"log"
|
||||
"math/rand"
|
||||
"sync"
|
||||
)
|
||||
|
||||
//go:embed ack_ru_v1.json
|
||||
var ackJSON []byte
|
||||
|
||||
// AckSchemaVersion — this family's own version. A file that changes on a
|
||||
// different day than the fallbacks cannot share their number (Vikunja #397).
|
||||
const AckSchemaVersion = 1
|
||||
|
||||
// The entry keys. Namespaced by family, because the floor map behind a nil deck
|
||||
// is process-wide.
|
||||
const (
|
||||
AckFact = "ack_fact"
|
||||
AckFactKey = "ack_fact_key"
|
||||
AckFactValue = "ack_fact_kv"
|
||||
AckNote = "ack_note"
|
||||
AckReminder = "ack_reminder"
|
||||
AckAct = "ack_act"
|
||||
AckTask = "ack_task"
|
||||
AckTaskUrgent = "ack_task_urgent"
|
||||
AckTaskDuplicate = "ack_task_duplicate"
|
||||
AckNudge = "ack_nudge"
|
||||
AckSnooze = "ack_snooze"
|
||||
AckGeneric = "ack_generic"
|
||||
AckQuietOn = "quiet_on"
|
||||
AckQuietOff = "quiet_off"
|
||||
|
||||
FailFact = "fail_fact"
|
||||
FailFactUnparsed = "fail_fact_unparsed"
|
||||
FailNote = "fail_note"
|
||||
FailReminder = "fail_reminder"
|
||||
FailReminderTime = "fail_reminder_time"
|
||||
FailTask = "fail_task"
|
||||
FailAck = "fail_ack"
|
||||
FailSnooze = "fail_snooze"
|
||||
FailQuiet = "fail_quiet"
|
||||
)
|
||||
|
||||
// ackKeys — every key the code requires the file to define.
|
||||
var ackKeys = []string{
|
||||
AckFact, AckFactKey, AckFactValue, AckNote, AckReminder, AckAct,
|
||||
AckTask, AckTaskUrgent, AckTaskDuplicate, AckNudge, AckSnooze, AckGeneric,
|
||||
AckQuietOn, AckQuietOff,
|
||||
FailFact, FailFactUnparsed, FailNote, FailReminder, FailReminderTime,
|
||||
FailTask, FailAck, FailSnooze, FailQuiet,
|
||||
}
|
||||
|
||||
// ackFloor — the literal each key falls back to when the file is unusable.
|
||||
// These are the exact strings that lived in Go before this file existed.
|
||||
var ackFloor = registerFloor(map[string]string{
|
||||
AckFact: "записала факт.",
|
||||
AckFactKey: "отметила: {key}",
|
||||
AckFactValue: "отметила: {key} = {value}",
|
||||
AckNote: "сохранила заметку.",
|
||||
AckReminder: "напомню.",
|
||||
AckAct: "ок, записала действие: {fn}",
|
||||
AckTask: "записала: {text}",
|
||||
AckTaskUrgent: "поняла, беру в работу: {text}",
|
||||
AckTaskDuplicate: "это уже в списке.",
|
||||
AckNudge: "отлично, отметила.",
|
||||
AckSnooze: "хорошо, вернусь к этому позже.",
|
||||
AckGeneric: "приняла.",
|
||||
AckQuietOn: "тихий режим включён. буду реже напоминать.",
|
||||
AckQuietOff: "тихий режим выключен.",
|
||||
|
||||
FailFact: "не получилось сохранить факт.",
|
||||
FailFactUnparsed: "не разобрала, что записать — попробуй иначе.",
|
||||
FailNote: "не получилось сохранить заметку.",
|
||||
FailReminder: "не получилось поставить напоминание.",
|
||||
FailReminderTime: "не получилось разобрать время напоминания.",
|
||||
FailTask: "не получилось записать задачу.",
|
||||
FailAck: "не получилось отметить.",
|
||||
FailSnooze: "не получилось отложить.",
|
||||
FailQuiet: "не получилось переключить тихий режим.",
|
||||
})
|
||||
|
||||
// Acks picks a hand-written Russian acknowledgement. Safe for concurrent use.
|
||||
type Acks struct{ d *deck }
|
||||
|
||||
// LoadAcks reads the embedded file. Pass a source to make the picking
|
||||
// reproducible in tests; nil seeds from the clock.
|
||||
func LoadAcks(src rand.Source) (*Acks, error) {
|
||||
d, err := loadDeck(ackJSON, AckSchemaVersion, ackKeys, ackFloor, src)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
// The three entries that exist to read his own words back. A variant
|
||||
// without the placeholder would confirm the capture and drop what was
|
||||
// captured, which reads as a successful save of nothing.
|
||||
for _, req := range []struct{ key, ph string }{
|
||||
{AckFactKey, "{key}"}, {AckFactValue, "{key}"}, {AckFactValue, "{value}"},
|
||||
{AckAct, "{fn}"}, {AckTask, "{text}"}, {AckTaskUrgent, "{text}"},
|
||||
} {
|
||||
if err := d.requirePlaceholder(req.key, req.ph); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
}
|
||||
return &Acks{d: d}, nil
|
||||
}
|
||||
|
||||
// deck reads through a nil *Acks, which is the unloadable-file case.
|
||||
func (a *Acks) deck() *deck {
|
||||
if a == nil {
|
||||
return nil
|
||||
}
|
||||
return a.d
|
||||
}
|
||||
|
||||
// Say returns one line for key, with his data filled into the frame. Pass nil
|
||||
// when the entry takes none.
|
||||
func (a *Acks) Say(key string, vars map[string]string) string {
|
||||
return a.deck().text(key, vars)
|
||||
}
|
||||
|
||||
// Variants returns every line the file can produce, for the persona scorer.
|
||||
func (a *Acks) Variants() []string { return a.deck().variants() }
|
||||
|
||||
var (
|
||||
ackOnce sync.Once
|
||||
acks *Acks
|
||||
)
|
||||
|
||||
// DefaultAcks returns the shared instance, loading it on first use. A broken
|
||||
// file logs once and leaves a nil *Acks, which still answers from ackFloor.
|
||||
func DefaultAcks() *Acks {
|
||||
ackOnce.Do(func() {
|
||||
a, err := LoadAcks(nil)
|
||||
if err != nil {
|
||||
log.Printf("phraser: acknowledgements unavailable, using the built-in lines: %v", err)
|
||||
return
|
||||
}
|
||||
acks = a
|
||||
})
|
||||
return acks
|
||||
}
|
||||
|
||||
// Ack — one acknowledgement line, the way every caller says it.
|
||||
func Ack(key string, vars map[string]string) string { return DefaultAcks().Say(key, vars) }
|
||||
|
||||
// IsAck reports whether text is a line key could have produced. For the daemon
|
||||
// tests, which can no longer compare against one literal.
|
||||
func IsAck(key string, vars map[string]string, text string) bool {
|
||||
return DefaultAcks().deck().matches(key, vars, text)
|
||||
}
|
||||
@@ -0,0 +1,181 @@
|
||||
package phraser
|
||||
|
||||
// deck — the mechanics every family of hand-written Russian lines shares.
|
||||
//
|
||||
// A family is one embedded JSON file: schema-versioned, several variants per
|
||||
// entry, never the same variant twice running, and a hard floor of Go literals
|
||||
// under it so a broken file cannot take her words away. fallbacks.go was the
|
||||
// first family (Vikunja #501) and acks.go the second, at which point copying
|
||||
// eighty lines of loader per family stopped being defensible.
|
||||
//
|
||||
// What stays per family: the file, the keys, the floor literals, the accessor
|
||||
// names, and any validation only that family can state.
|
||||
|
||||
import (
|
||||
"encoding/json"
|
||||
"fmt"
|
||||
"math/rand"
|
||||
"strings"
|
||||
"sync"
|
||||
"time"
|
||||
)
|
||||
|
||||
// deckEntry — one line she can say, in as many wordings as the file gives.
|
||||
type deckEntry struct {
|
||||
// Fixed — one variant, never picked between. For wording that must not
|
||||
// drift from turn to turn, like a phrase naming one specific gap.
|
||||
Fixed bool `json:"fixed"`
|
||||
Variants []string `json:"variants"`
|
||||
}
|
||||
|
||||
type deckFile struct {
|
||||
SchemaVersion int `json:"schema_version"`
|
||||
Name string `json:"name"`
|
||||
Notes []string `json:"notes"`
|
||||
Entries map[string]deckEntry `json:"entries"`
|
||||
}
|
||||
|
||||
// deck picks a line. Safe for concurrent use. A nil *deck answers from the
|
||||
// floor, which is what an unloadable file leaves behind.
|
||||
type deck struct {
|
||||
mu sync.Mutex
|
||||
rnd *rand.Rand
|
||||
last map[string]string
|
||||
file deckFile
|
||||
keys []string
|
||||
floor map[string]string
|
||||
}
|
||||
|
||||
// loadDeck parses raw, checks the version and every required key, and seeds the
|
||||
// picker. Pass a source to make the picking reproducible in tests; nil seeds
|
||||
// from the clock.
|
||||
func loadDeck(raw []byte, version int, keys []string, floor map[string]string, src rand.Source) (*deck, error) {
|
||||
var f deckFile
|
||||
if err := json.Unmarshal(raw, &f); err != nil {
|
||||
return nil, fmt.Errorf("parse: %w", err)
|
||||
}
|
||||
if f.SchemaVersion != version {
|
||||
return nil, fmt.Errorf("schema_version %d, want %d", f.SchemaVersion, version)
|
||||
}
|
||||
for _, k := range keys {
|
||||
e, ok := f.Entries[k]
|
||||
if !ok || len(e.Variants) == 0 {
|
||||
return nil, fmt.Errorf("entry %q is missing or empty", k)
|
||||
}
|
||||
if e.Fixed && len(e.Variants) != 1 {
|
||||
return nil, fmt.Errorf("entry %q is fixed but has %d variants", k, len(e.Variants))
|
||||
}
|
||||
}
|
||||
if src == nil {
|
||||
src = rand.NewSource(time.Now().UnixNano())
|
||||
}
|
||||
return &deck{rnd: rand.New(src), last: map[string]string{}, file: f, keys: keys, floor: floor}, nil
|
||||
}
|
||||
|
||||
// requirePlaceholder fails the load when a variant of key does not use ph. For
|
||||
// an entry whose whole job is to read something back, a variant without the
|
||||
// placeholder silently drops it.
|
||||
func (d *deck) requirePlaceholder(key, ph string) error {
|
||||
for _, v := range d.file.Entries[key].Variants {
|
||||
if !strings.Contains(v, ph) {
|
||||
return fmt.Errorf("%q variant %q does not use %s", key, v, ph)
|
||||
}
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
// text returns one variant for key with the placeholders filled in. A nil
|
||||
// receiver answers from the floor, so no caller checks whether the file loaded.
|
||||
func (d *deck) text(key string, vars map[string]string) string {
|
||||
tmpl := ""
|
||||
if d != nil {
|
||||
if e, ok := d.file.Entries[key]; ok && len(e.Variants) > 0 {
|
||||
tmpl = d.pick(key, e)
|
||||
}
|
||||
}
|
||||
if tmpl == "" {
|
||||
tmpl = floorOf(d, key)
|
||||
}
|
||||
return fill(tmpl, vars)
|
||||
}
|
||||
|
||||
// matches reports whether text is a line key could have produced. A caller that
|
||||
// has to recognise one of these lines cannot compare against a literal any more.
|
||||
func (d *deck) matches(key string, vars map[string]string, text string) bool {
|
||||
if fill(floorOf(d, key), vars) == text {
|
||||
return true
|
||||
}
|
||||
if d == nil {
|
||||
return false
|
||||
}
|
||||
for _, v := range d.file.Entries[key].Variants {
|
||||
if fill(v, vars) == text {
|
||||
return true
|
||||
}
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
// variants returns every line the file can produce, in key order, for the
|
||||
// persona scorer. Stable order so a failure names the same variant twice.
|
||||
func (d *deck) variants() []string {
|
||||
if d == nil {
|
||||
return nil
|
||||
}
|
||||
var out []string
|
||||
for _, k := range d.keys {
|
||||
out = append(out, d.file.Entries[k].Variants...)
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
// pick chooses at random, skipping whatever this entry said last time.
|
||||
func (d *deck) pick(key string, e deckEntry) string {
|
||||
d.mu.Lock()
|
||||
defer d.mu.Unlock()
|
||||
|
||||
choices := e.Variants
|
||||
if len(choices) > 1 {
|
||||
fresh := make([]string, 0, len(choices))
|
||||
for _, v := range choices {
|
||||
if v != d.last[key] {
|
||||
fresh = append(fresh, v)
|
||||
}
|
||||
}
|
||||
if len(fresh) > 0 {
|
||||
choices = fresh
|
||||
}
|
||||
}
|
||||
got := choices[d.rnd.Intn(len(choices))]
|
||||
d.last[key] = got
|
||||
return got
|
||||
}
|
||||
|
||||
// floorOf reads the Go literal behind key, and works on a nil deck because that
|
||||
// is exactly the case it exists for. The per-family map is the source of truth.
|
||||
func floorOf(d *deck, key string) string {
|
||||
if d != nil && d.floor != nil {
|
||||
return d.floor[key]
|
||||
}
|
||||
return deckFloors[key]
|
||||
}
|
||||
|
||||
// deckFloors — every family's floor literals in one map, so a nil deck still
|
||||
// finds them. Families register at init; the keys are namespaced by family.
|
||||
var deckFloors = map[string]string{}
|
||||
|
||||
func registerFloor(floor map[string]string) map[string]string {
|
||||
for k, v := range floor {
|
||||
deckFloors[k] = v
|
||||
}
|
||||
return floor
|
||||
}
|
||||
|
||||
// fill substitutes {name} for each var. A placeholder with no value is left
|
||||
// alone rather than blanked, so a missing value is visible instead of silent.
|
||||
func fill(tmpl string, vars map[string]string) string {
|
||||
for k, v := range vars {
|
||||
tmpl = strings.ReplaceAll(tmpl, "{"+k+"}", v)
|
||||
}
|
||||
return tmpl
|
||||
}
|
||||
@@ -0,0 +1,47 @@
|
||||
package eval
|
||||
|
||||
import (
|
||||
"math/rand"
|
||||
"strings"
|
||||
"testing"
|
||||
|
||||
"github.com/kami/maven/internal/phraser"
|
||||
)
|
||||
|
||||
// TestFallbackPersona scores every line in fallbacks_ru_v1.json and
|
||||
// ack_ru_v1.json on the persona checks the nudges already pass. These lines are
|
||||
// heard out loud and they live in a JSON file now, so a reworded variant that
|
||||
// says "рад" or "вы" would otherwise reach him with nothing in between.
|
||||
//
|
||||
// Only the persona checks run. Mood and topic belong to a nudge, and these are
|
||||
// not nudges.
|
||||
func TestFallbackPersona(t *testing.T) {
|
||||
fb, err := phraser.LoadFallbacks(rand.NewSource(20260804))
|
||||
if err != nil {
|
||||
t.Fatalf("LoadFallbacks: %v", err)
|
||||
}
|
||||
persona := map[string]bool{
|
||||
CheckLang: true, CheckFeminine: true, CheckHisGender: true,
|
||||
CheckAddress: true, CheckCringe: true, CheckLength: true,
|
||||
}
|
||||
ack, err := phraser.LoadAcks(rand.NewSource(20260804))
|
||||
if err != nil {
|
||||
t.Fatalf("LoadAcks: %v", err)
|
||||
}
|
||||
variants := append(fb.Variants(), ack.Variants()...)
|
||||
if len(variants) == 0 {
|
||||
t.Fatal("no variants — the file loaded empty")
|
||||
}
|
||||
for _, v := range variants {
|
||||
// The placeholders stand for his own words and carry no persona.
|
||||
body := v
|
||||
for _, ph := range []string{"{sources}", "{key}", "{value}", "{fn}", "{text}"} {
|
||||
body = strings.ReplaceAll(body, ph, "вода")
|
||||
}
|
||||
for _, r := range RunChecks(Case{}, body, "neutral") {
|
||||
if persona[r.Name] && !r.Pass {
|
||||
t.Errorf("%q fails %s: %s", v, r.Name, r.Detail)
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -26,20 +26,22 @@ import (
|
||||
"time"
|
||||
|
||||
"github.com/kami/maven/internal/dialogue"
|
||||
"github.com/kami/maven/internal/router"
|
||||
)
|
||||
|
||||
//go:embed talk_v1.json
|
||||
var talkFixtureJSON []byte
|
||||
|
||||
// The three phrasing paths under test. Values match the fixture's "path" field.
|
||||
// The phrasing paths under test. Values match the fixture's "path" field.
|
||||
const (
|
||||
PathChat = "chat" // PhraseChat
|
||||
PathQuery = "query" // PhraseQuery with notes
|
||||
PathKnowledge = "knowledge" // PhraseQuery with no notes
|
||||
PathReply = "reply" // PhraseReply, the reactive confirmation
|
||||
)
|
||||
|
||||
// TalkPaths — report order.
|
||||
var TalkPaths = []string{PathChat, PathQuery, PathKnowledge}
|
||||
var TalkPaths = []string{PathChat, PathQuery, PathKnowledge, PathReply}
|
||||
|
||||
// TalkCheckNames — the checks that apply to a free-form reply, in report order.
|
||||
// Deliberately a subset of CheckNames: length, mood and "no questions" are nudge
|
||||
@@ -58,17 +60,30 @@ var TalkCheckNames = []string{
|
||||
// WantAny is the on-topic contract: at least one lowercased fragment must appear
|
||||
// in the reply. Fragments are stems ("пароль" → "парол") so declension does not
|
||||
// defeat them.
|
||||
//
|
||||
// Intent, Key and Value carry the reply path's decision: that path is phrased
|
||||
// from what the router already resolved, not from the raw utterance. Utterance
|
||||
// stays filled anyway, because it is what a human reads in the report.
|
||||
type TalkCase struct {
|
||||
ID string `json:"id"`
|
||||
Path string `json:"path"`
|
||||
Utterance string `json:"utterance"`
|
||||
History []string `json:"history,omitempty"`
|
||||
Notes []string `json:"notes,omitempty"`
|
||||
Intent string `json:"intent,omitempty"`
|
||||
Key string `json:"key,omitempty"`
|
||||
Value string `json:"value,omitempty"`
|
||||
WantAny []string `json:"want_any"`
|
||||
Tags []string `json:"tags,omitempty"`
|
||||
Note string `json:"note,omitempty"`
|
||||
}
|
||||
|
||||
// TalkSchemaVersion — the version this loader understands. Separate from the
|
||||
// nudge fixture's SchemaVersion: the two fixtures have different shapes and
|
||||
// change on different days, and one shared constant would force a bump on the
|
||||
// fixture that did not move.
|
||||
const TalkSchemaVersion = 1
|
||||
|
||||
// TalkFixture — the versioned envelope, same gating as Fixture.
|
||||
type TalkFixture struct {
|
||||
SchemaVersion int `json:"schema_version"`
|
||||
@@ -83,8 +98,8 @@ func LoadTalk() (TalkFixture, error) {
|
||||
if err := json.Unmarshal(talkFixtureJSON, &f); err != nil {
|
||||
return TalkFixture{}, fmt.Errorf("parse talk fixture: %w", err)
|
||||
}
|
||||
if f.SchemaVersion != SchemaVersion {
|
||||
return TalkFixture{}, fmt.Errorf("talk fixture schema_version %d, want %d", f.SchemaVersion, SchemaVersion)
|
||||
if f.SchemaVersion != TalkSchemaVersion {
|
||||
return TalkFixture{}, fmt.Errorf("talk fixture schema_version %d, want %d", f.SchemaVersion, TalkSchemaVersion)
|
||||
}
|
||||
if len(f.Cases) == 0 {
|
||||
return TalkFixture{}, fmt.Errorf("talk fixture has no cases")
|
||||
@@ -92,13 +107,27 @@ func LoadTalk() (TalkFixture, error) {
|
||||
return f, nil
|
||||
}
|
||||
|
||||
// Talker — the two methods a conversational path must have to be scorable.
|
||||
// *phraser.LLMPhraser satisfies it; same trick as Nudger.
|
||||
// Talker — the methods a conversational path must have to be scorable.
|
||||
// *phraser.LLMPhraser satisfies the first two; *phraser.Replier satisfies the
|
||||
// third, so a run that scores all four paths passes a Pair.
|
||||
type Talker interface {
|
||||
PhraseChat(ctx context.Context, utterance string, history []dialogue.Turn) (string, error)
|
||||
PhraseQuery(ctx context.Context, utterance string, notes []string) (string, error)
|
||||
}
|
||||
|
||||
// Confirmer — the reply path. *phraser.Replier satisfies it.
|
||||
type Confirmer interface {
|
||||
PhraseReply(ctx context.Context, d router.Decision) (string, error)
|
||||
}
|
||||
|
||||
// Pair joins the two objects the daemon wires separately — the phraser and the
|
||||
// replier — so one ScoreTalk call covers every path Maven speaks through. A bare
|
||||
// Talker still works; its reply cases score as errors, which is honest.
|
||||
type Pair struct {
|
||||
Talker
|
||||
Confirmer
|
||||
}
|
||||
|
||||
// TalkOutcome — one scored case.
|
||||
type TalkOutcome struct {
|
||||
Case TalkCase
|
||||
@@ -194,10 +223,30 @@ func (c TalkCase) run(ctx context.Context, t Talker) (string, error) {
|
||||
return t.PhraseQuery(ctx, c.Utterance, c.Notes)
|
||||
case PathKnowledge:
|
||||
return t.PhraseQuery(ctx, c.Utterance, nil)
|
||||
case PathReply:
|
||||
conf, ok := t.(Confirmer)
|
||||
if !ok {
|
||||
return "", fmt.Errorf("target cannot phrase replies — pass a Pair")
|
||||
}
|
||||
return conf.PhraseReply(ctx, c.decision())
|
||||
}
|
||||
return "", fmt.Errorf("unknown path %q", c.Path)
|
||||
}
|
||||
|
||||
// decision rebuilds what the router would have handed the replier. Text is the
|
||||
// utterance for a note or a reminder, which is what the router puts there.
|
||||
func (c TalkCase) decision() router.Decision {
|
||||
return router.Decision{
|
||||
Intent: router.Intent(c.Intent),
|
||||
Slots: router.Slots{
|
||||
Key: c.Key,
|
||||
Value: c.Value,
|
||||
Text: c.Utterance,
|
||||
HasKey: c.Key != "",
|
||||
},
|
||||
}
|
||||
}
|
||||
|
||||
func (c TalkCase) turns() []dialogue.Turn {
|
||||
turns := make([]dialogue.Turn, 0, len(c.History))
|
||||
for _, h := range c.History {
|
||||
|
||||
@@ -11,6 +11,7 @@ import (
|
||||
"github.com/kami/maven/internal/llm"
|
||||
"github.com/kami/maven/internal/persona"
|
||||
"github.com/kami/maven/internal/phraser"
|
||||
"github.com/kami/maven/internal/router"
|
||||
)
|
||||
|
||||
// perPathMinimum — the resolution floor. A per-path score built on a handful of
|
||||
@@ -36,6 +37,10 @@ func TestTalkFixture(t *testing.T) {
|
||||
|
||||
switch c.Path {
|
||||
case PathChat, PathQuery, PathKnowledge:
|
||||
case PathReply:
|
||||
if c.Intent == "" {
|
||||
t.Errorf("%s: reply case has no intent — the replier is phrased from the decision", c.ID)
|
||||
}
|
||||
default:
|
||||
t.Errorf("%s: unknown path %q", c.ID, c.Path)
|
||||
}
|
||||
@@ -69,10 +74,15 @@ type fakeTalker struct{ reply string }
|
||||
func (f fakeTalker) PhraseChat(context.Context, string, []dialogue.Turn) (string, error) {
|
||||
return f.reply, nil
|
||||
}
|
||||
|
||||
func (f fakeTalker) PhraseQuery(context.Context, string, []string) (string, error) {
|
||||
return f.reply, nil
|
||||
}
|
||||
|
||||
func (f fakeTalker) PhraseReply(context.Context, router.Decision) (string, error) {
|
||||
return f.reply, nil
|
||||
}
|
||||
|
||||
// TestScoreTalkCounts — a reply that fails on purpose must be counted on every
|
||||
// path, so a real run cannot report a hidden zero.
|
||||
func TestScoreTalkCounts(t *testing.T) {
|
||||
@@ -104,7 +114,7 @@ func TestScoreTalkCounts(t *testing.T) {
|
||||
}
|
||||
}
|
||||
|
||||
// TestLLMTalkBaseline — the resident model on the three conversational paths.
|
||||
// TestLLMTalkBaseline — the resident model on all four phrasing paths.
|
||||
// Opt-in exactly like TestLLMPhrasingBaseline: CI has no model and a run costs
|
||||
// minutes on the CPU target.
|
||||
//
|
||||
@@ -132,32 +142,32 @@ func TestLLMTalkBaseline(t *testing.T) {
|
||||
p := phraser.NewLLMPhraserAt(base, cfg)
|
||||
defer p.Close()
|
||||
|
||||
// Unreachable server is fatal here, not a logged warning, and that differs
|
||||
// from the nudge test on purpose. PhraseNudge returns its errors, so a dead
|
||||
// server there shows up honestly in the Errors column. PhraseChat and
|
||||
// PhraseQuery do NOT: they swallow every failure and return a canned string
|
||||
// ("поговорили.", "не знаю.", "вот что я нашла: …"). So on these three paths
|
||||
// a dead server produces a full report with 0 errors and a terrible score —
|
||||
// a number that looks like bad phrasing and is really no phrasing at all.
|
||||
// Refusing to score without a confirmed model is the only guard available
|
||||
// until the phraser reports its failures (Vikunja #397).
|
||||
// The model id names the run in the report. Since Vikunja #397 every path
|
||||
// returns its errors, so a server that dies mid-run shows up in the Errors
|
||||
// column instead of scoring as bad phrasing — the before-and-after probe that
|
||||
// used to stand in for that is gone.
|
||||
model, err := llm.ModelID(ctx, base)
|
||||
if err != nil {
|
||||
t.Fatalf("no model at %s: %v — refusing to score, these paths hide their errors "+
|
||||
"and would report a plausible-looking result off a dead server", base, err)
|
||||
t.Fatalf("no model at %s: %v", base, err)
|
||||
}
|
||||
t.Logf("scoring model %s at %s", model, base)
|
||||
|
||||
rep, err := ScoreTalk(ctx, "llm ("+model+", built-in persona)", p, f)
|
||||
// The reply path is a separate object in the daemon too: the phraser owns its
|
||||
// own llama-server, the replier is handed an llm.Client. Pair scores both.
|
||||
block := func() string { return persona.Facts{}.Block(time.Now()) }
|
||||
target := Pair{Talker: p, Confirmer: phraser.NewReplier(llm.New(base, cfg.Timeout), block)}
|
||||
|
||||
rep, err := ScoreTalk(ctx, "llm ("+model+", built-in persona)", target, f)
|
||||
if err != nil {
|
||||
t.Fatalf("ScoreTalk: %v", err)
|
||||
}
|
||||
t.Log("\n" + rep.String() + "\nreplies:\n" + rep.Replies() + "\nfailures:\n" + rep.Failures())
|
||||
|
||||
// And again afterwards: the run takes minutes, and a server that died or got
|
||||
// OOM-killed halfway through would leave the first cases scored and the rest
|
||||
// silently canned. Checking only at the start would not catch that.
|
||||
if _, err := llm.ModelID(ctx, base); err != nil {
|
||||
t.Fatalf("model at %s went away during the run: %v — the score above is not trustworthy", base, err)
|
||||
// A run where nothing was phrased is not a low score, it is no measurement.
|
||||
if rep.Errors == rep.Total {
|
||||
t.Fatalf("every case errored — nothing was measured, the score above is not a phrasing result")
|
||||
}
|
||||
if rep.Errors > 0 {
|
||||
t.Logf("%d/%d cases errored — those are model failures, not phrasing failures", rep.Errors, rep.Total)
|
||||
}
|
||||
}
|
||||
|
||||
@@ -222,6 +222,90 @@
|
||||
"utterance": "почему гром слышно позже молнии?",
|
||||
"want_any": ["звук", "све", "быстр", "гром", "молни"],
|
||||
"tags": ["general"]
|
||||
},
|
||||
{
|
||||
"id": "reply-fact-coffee",
|
||||
"path": "reply",
|
||||
"intent": "fact",
|
||||
"key": "кофе",
|
||||
"value": "закончился",
|
||||
"utterance": "кофе закончился",
|
||||
"want_any": ["коф"],
|
||||
"tags": ["fact"],
|
||||
"note": "The plainest confirmation there is, and the sentence he hears most often."
|
||||
},
|
||||
{
|
||||
"id": "reply-fact-weight",
|
||||
"path": "reply",
|
||||
"intent": "fact",
|
||||
"key": "вес",
|
||||
"value": "82",
|
||||
"utterance": "мой вес 82",
|
||||
"want_any": ["вес", "82"],
|
||||
"tags": ["fact", "number"],
|
||||
"note": "A number must survive into the confirmation; a paraphrase that drops it is useless."
|
||||
},
|
||||
{
|
||||
"id": "reply-fact-pill",
|
||||
"path": "reply",
|
||||
"intent": "fact",
|
||||
"key": "таблетки",
|
||||
"value": "выпил",
|
||||
"utterance": "таблетки выпил",
|
||||
"want_any": ["таблетк"],
|
||||
"tags": ["fact", "feminine"],
|
||||
"note": "He says 'выпил', masculine and about himself. She must not copy the form onto herself."
|
||||
},
|
||||
{
|
||||
"id": "reply-note-router",
|
||||
"path": "reply",
|
||||
"intent": "note",
|
||||
"utterance": "роутер перезагружается сам по ночам",
|
||||
"want_any": ["роутер"],
|
||||
"tags": ["note"]
|
||||
},
|
||||
{
|
||||
"id": "reply-note-long",
|
||||
"path": "reply",
|
||||
"intent": "note",
|
||||
"utterance": "если диск снова отвалится, посмотреть кабель, а не контроллер, в прошлый раз был кабель",
|
||||
"want_any": ["диск", "кабел"],
|
||||
"tags": ["note", "length"],
|
||||
"note": "A long note baits a long confirmation. One sentence is the contract."
|
||||
},
|
||||
{
|
||||
"id": "reply-reminder-evening",
|
||||
"path": "reply",
|
||||
"intent": "reminder",
|
||||
"utterance": "напомни вечером полить цветы",
|
||||
"want_any": ["цвет", "полит", "вечер"],
|
||||
"tags": ["reminder"]
|
||||
},
|
||||
{
|
||||
"id": "reply-reminder-tomorrow",
|
||||
"path": "reply",
|
||||
"intent": "reminder",
|
||||
"utterance": "напомни завтра позвонить в поликлинику",
|
||||
"want_any": ["поликлиник", "позвон", "звон"],
|
||||
"tags": ["reminder"]
|
||||
},
|
||||
{
|
||||
"id": "reply-formality-bait",
|
||||
"path": "reply",
|
||||
"intent": "note",
|
||||
"utterance": "запишите пожалуйста что счётчики я сдал",
|
||||
"want_any": ["счётчик", "счетчик"],
|
||||
"tags": ["note", "persona-bait", "address"],
|
||||
"note": "Polite plural in the input. The confirmation must still be на ты."
|
||||
},
|
||||
{
|
||||
"id": "reply-question-bait",
|
||||
"path": "reply",
|
||||
"intent": "note",
|
||||
"utterance": "надо купить фильтр для воды, не помню какой",
|
||||
"want_any": ["фильтр"],
|
||||
"tags": ["note", "no-question"],
|
||||
"note": "An unresolved note invites her to ask which filter. A confirmation does not ask."
|
||||
}
|
||||
]
|
||||
}
|
||||
|
||||
@@ -0,0 +1,80 @@
|
||||
package phraser
|
||||
|
||||
import (
|
||||
"context"
|
||||
"net/http"
|
||||
"net/http/httptest"
|
||||
"strings"
|
||||
"testing"
|
||||
)
|
||||
|
||||
// isFallback — the text she says is picked from that entry's variants, so a test
|
||||
// pins the entry rather than the wording. Pinning one line would make editing
|
||||
// fallbacks_ru_v1.json break Go tests, which is the coupling this file removed.
|
||||
func isFallback(t *testing.T, key, sources, got string) bool {
|
||||
t.Helper()
|
||||
return DefaultFallbacks().deck().matches(key, map[string]string{"sources": sources}, got)
|
||||
}
|
||||
|
||||
// A dead server must be distinguishable from bad phrasing. Both PhraseChat and
|
||||
// PhraseQuery keep the turn alive with canned text — and every one of those
|
||||
// lines is also a legitimate reply, so the text alone cannot say which happened.
|
||||
// The error is the only signal, and before Vikunja #397 it was dropped: the talk
|
||||
// scorer reported a full run with zero errors off a server that answered nothing.
|
||||
func TestPhrasingReportsTheFailureWithTheFallback(t *testing.T) {
|
||||
srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
|
||||
http.Error(w, "model not loaded", http.StatusServiceUnavailable)
|
||||
}))
|
||||
t.Cleanup(srv.Close)
|
||||
p := NewLLMPhraserAt(srv.URL, Config{})
|
||||
|
||||
cases := []struct {
|
||||
name string
|
||||
call func() (string, error)
|
||||
key string
|
||||
sources string
|
||||
}{
|
||||
{"chat", func() (string, error) {
|
||||
return p.PhraseChat(context.Background(), "как дела", nil)
|
||||
}, fbChat, ""},
|
||||
{"knowledge", func() (string, error) {
|
||||
return p.PhraseQuery(context.Background(), "кто написал войну и мир", nil)
|
||||
}, fbQueryUnknown, ""},
|
||||
{"evidence", func() (string, error) {
|
||||
return p.PhraseQuery(context.Background(), "сколько воды я выпил", []string{"два литра"})
|
||||
}, fbQuerySources, "два литра"},
|
||||
}
|
||||
for _, c := range cases {
|
||||
t.Run(c.name, func(t *testing.T) {
|
||||
got, err := c.call()
|
||||
if err == nil {
|
||||
t.Fatalf("no error from a dead server; the scorer would count this as bad phrasing")
|
||||
}
|
||||
if !isFallback(t, c.key, c.sources, got) {
|
||||
t.Errorf("fallback text = %q, want a %q variant — the daemon still has to say something", got, c.key)
|
||||
}
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
// An empty answer is a failure too: the server is up and produced no tokens,
|
||||
// which is not an answer and must not score as one.
|
||||
func TestEmptyKnowledgeAnswerIsAnError(t *testing.T) {
|
||||
srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
|
||||
w.Header().Set("Content-Type", "application/json")
|
||||
w.Write([]byte(`{"choices":[{"message":{"content":""}}]}`))
|
||||
}))
|
||||
t.Cleanup(srv.Close)
|
||||
p := NewLLMPhraserAt(srv.URL, Config{})
|
||||
|
||||
got, err := p.PhraseQuery(context.Background(), "кто написал войну и мир", nil)
|
||||
if err == nil {
|
||||
t.Fatal("an empty response scored as an answer")
|
||||
}
|
||||
if !isFallback(t, fbQueryUnknown, "", got) {
|
||||
t.Errorf("fallback text = %q, want a %q variant", got, fbQueryUnknown)
|
||||
}
|
||||
if !strings.Contains(err.Error(), "empty") {
|
||||
t.Errorf("error = %v; want it to name the empty response", err)
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,138 @@
|
||||
package phraser
|
||||
|
||||
// The phrasing fallbacks — what she says when the model gave her nothing usable.
|
||||
//
|
||||
// They were four string literals spread across phraser.go, llmphraser.go and
|
||||
// cmd/mavend/worldmodel.go. Every one of them is a line he hears out loud, so
|
||||
// rewording one was a Go edit, a rebuild and a redeploy for what is product copy.
|
||||
//
|
||||
// The floor under the floor is deliberate. These strings exist because something
|
||||
// already failed, so a broken template file must not be able to take the last
|
||||
// words she has: every accessor falls back to the literal it replaced.
|
||||
|
||||
import (
|
||||
_ "embed"
|
||||
"log"
|
||||
"math/rand"
|
||||
"sync"
|
||||
)
|
||||
|
||||
//go:embed fallbacks_ru_v1.json
|
||||
var fallbackJSON []byte
|
||||
|
||||
// FallbackSchemaVersion — the version this code understands. Its own constant,
|
||||
// not shared with the nudge templates or the eval fixtures: two files that change
|
||||
// on different days cannot be versioned by one number (Vikunja #397).
|
||||
const FallbackSchemaVersion = 1
|
||||
|
||||
// The entry keys. Every one of them is read by a method below, so a typo in the
|
||||
// file is caught at load rather than at the moment she needs the words.
|
||||
const (
|
||||
fbChat = "chat"
|
||||
fbQueryUnknown = "query_unknown"
|
||||
fbQuerySources = "query_sources"
|
||||
fbWorldGap = "world_gap"
|
||||
)
|
||||
|
||||
// fbKeys — every key the code requires the file to define.
|
||||
var fbKeys = []string{fbChat, fbQueryUnknown, fbQuerySources, fbWorldGap}
|
||||
|
||||
// hardFloor — the literal each key falls back to when the file is unusable.
|
||||
// These are the exact strings that lived in Go before this file existed.
|
||||
var hardFloor = registerFloor(map[string]string{
|
||||
fbChat: "даже не знаю, что сказать.",
|
||||
fbQueryUnknown: "не знаю.",
|
||||
fbQuerySources: "вот что я нашла: {sources}",
|
||||
fbWorldGap: "сейчас не могу ответить — большая модель недоступна, а придумывать не хочу.",
|
||||
})
|
||||
|
||||
// Fallbacks picks a hand-written Russian fallback line. Safe for concurrent use.
|
||||
type Fallbacks struct{ d *deck }
|
||||
|
||||
// LoadFallbacks reads the embedded file. Pass a source to make the picking
|
||||
// reproducible in tests; nil seeds from the clock.
|
||||
func LoadFallbacks(src rand.Source) (*Fallbacks, error) {
|
||||
d, err := loadDeck(fallbackJSON, FallbackSchemaVersion, fbKeys, hardFloor, src)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
// query_sources is the one entry whose whole job is to read something back.
|
||||
if err := d.requirePlaceholder(fbQuerySources, "{sources}"); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
return &Fallbacks{d: d}, nil
|
||||
}
|
||||
|
||||
// deck reads through a nil *Fallbacks, which is the unloadable-file case.
|
||||
func (f *Fallbacks) deck() *deck {
|
||||
if f == nil {
|
||||
return nil
|
||||
}
|
||||
return f.d
|
||||
}
|
||||
|
||||
// Chat — nothing usable came back on the chat path.
|
||||
func (f *Fallbacks) Chat() string { return f.deck().text(fbChat, nil) }
|
||||
|
||||
// Unknown — a question she cannot answer and will not guess at.
|
||||
func (f *Fallbacks) Unknown() string { return f.deck().text(fbQueryUnknown, nil) }
|
||||
|
||||
// FromSources — read back what she was handed, because phrasing it failed.
|
||||
func (f *Fallbacks) FromSources(sources string) string {
|
||||
return f.deck().text(fbQuerySources, map[string]string{"sources": sources})
|
||||
}
|
||||
|
||||
// WorldGap — the world model is the one configured to answer and it is not
|
||||
// answering. Fixed wording: it names a specific gap, and a variant set here
|
||||
// would let "the big model is asleep" drift into "I don't know".
|
||||
func (f *Fallbacks) WorldGap() string { return f.deck().text(fbWorldGap, nil) }
|
||||
|
||||
// Variants returns every line the file can produce, for the persona scorer.
|
||||
func (f *Fallbacks) Variants() []string { return f.deck().variants() }
|
||||
|
||||
// The process-wide instance. Package-level because these lines are needed on
|
||||
// paths that have no phraser to hand — cmd/mavend names the world gap without
|
||||
// one — and because a template file that is embedded and validated at load has
|
||||
// nothing per-instance to configure.
|
||||
var (
|
||||
fallbackOnce sync.Once
|
||||
fallbacks *Fallbacks
|
||||
)
|
||||
|
||||
// DefaultFallbacks returns the shared instance, loading it on first use. A
|
||||
// broken file logs once and leaves a nil *Fallbacks, which still answers from
|
||||
// hardFloor — a daemon must not fail to boot over its own copy deck.
|
||||
func DefaultFallbacks() *Fallbacks {
|
||||
fallbackOnce.Do(func() {
|
||||
fb, err := LoadFallbacks(nil)
|
||||
if err != nil {
|
||||
log.Printf("phraser: fallbacks unavailable, using the built-in lines: %v", err)
|
||||
return
|
||||
}
|
||||
fallbacks = fb
|
||||
})
|
||||
return fallbacks
|
||||
}
|
||||
|
||||
// ChatFallback — what she says when the chat path produced nothing.
|
||||
func ChatFallback() string { return DefaultFallbacks().Chat() }
|
||||
|
||||
// UnknownFallback — what she says when she has no answer and will not invent one.
|
||||
func UnknownFallback() string { return DefaultFallbacks().Unknown() }
|
||||
|
||||
// SourcesFallback — read the sources back rather than ship a broken fragment.
|
||||
func SourcesFallback(sources string) string { return DefaultFallbacks().FromSources(sources) }
|
||||
|
||||
// WorldGap — what he hears when the world model is configured and unreachable.
|
||||
func WorldGap() string { return DefaultFallbacks().WorldGap() }
|
||||
|
||||
// IsUnknownFallback reports whether text is one of her "I do not know" lines.
|
||||
// The daemon tests read it to tell an answer from a shrug.
|
||||
func IsUnknownFallback(text string) bool {
|
||||
return DefaultFallbacks().deck().matches(fbQueryUnknown, nil, text)
|
||||
}
|
||||
|
||||
// IsSourcesFallback reports whether text is sources read back verbatim.
|
||||
func IsSourcesFallback(text, sources string) bool {
|
||||
return DefaultFallbacks().deck().matches(fbQuerySources, map[string]string{"sources": sources}, text)
|
||||
}
|
||||
@@ -0,0 +1,42 @@
|
||||
{
|
||||
"schema_version": 1,
|
||||
"name": "russian phrasing fallbacks v1",
|
||||
"notes": [
|
||||
"What she says when the model gave her nothing usable. 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, never он/его about him. No pet names.",
|
||||
"These are heard after a failure, so they stay short and admit the gap. None of them may claim knowledge she does not have.",
|
||||
"Placeholders: {sources} the notes or passages she was handed. A variant whose placeholder has no value is skipped, so every entry needs at least one variant with no placeholder — except query_sources, which exists only to read sources back.",
|
||||
"fixed: true means exactly one variant and no picking. Used where the wording is load-bearing and must not drift between turns."
|
||||
],
|
||||
"entries": {
|
||||
"chat": {
|
||||
"variants": [
|
||||
"даже не знаю, что сказать.",
|
||||
"не могу найти слов.",
|
||||
"мысль ускользнула, повтори?",
|
||||
"у меня сейчас пусто в голове."
|
||||
]
|
||||
},
|
||||
"query_unknown": {
|
||||
"variants": [
|
||||
"не знаю.",
|
||||
"не знаю, честно.",
|
||||
"тут я пас.",
|
||||
"не скажу, не знаю."
|
||||
]
|
||||
},
|
||||
"query_sources": {
|
||||
"variants": [
|
||||
"вот что я нашла: {sources}",
|
||||
"нашла вот это: {sources}",
|
||||
"есть только это: {sources}"
|
||||
]
|
||||
},
|
||||
"world_gap": {
|
||||
"fixed": true,
|
||||
"variants": [
|
||||
"сейчас не могу ответить — большая модель недоступна, а придумывать не хочу."
|
||||
]
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,74 @@
|
||||
package phraser
|
||||
|
||||
import (
|
||||
"math/rand"
|
||||
"strings"
|
||||
"testing"
|
||||
)
|
||||
|
||||
// The embedded file must load, or the daemon speaks from hardFloor and nobody
|
||||
// finds out until he hears the wrong words.
|
||||
func TestFallbacksLoad(t *testing.T) {
|
||||
fb, err := LoadFallbacks(rand.NewSource(1))
|
||||
if err != nil {
|
||||
t.Fatalf("LoadFallbacks: %v", err)
|
||||
}
|
||||
if got := fb.FromSources("два литра"); !strings.Contains(got, "два литра") {
|
||||
t.Errorf("FromSources = %q, want the sources in it", got)
|
||||
}
|
||||
if fb.WorldGap() != hardFloor[fbWorldGap] {
|
||||
t.Errorf("WorldGap = %q, want the fixed wording %q", fb.WorldGap(), hardFloor[fbWorldGap])
|
||||
}
|
||||
}
|
||||
|
||||
// A broken or missing file must not take her last words away: every accessor
|
||||
// answers from the literal it replaced.
|
||||
func TestNilFallbacksAnswerFromTheHardFloor(t *testing.T) {
|
||||
var fb *Fallbacks
|
||||
if got := fb.Chat(); got != hardFloor[fbChat] {
|
||||
t.Errorf("Chat = %q, want %q", got, hardFloor[fbChat])
|
||||
}
|
||||
if got := fb.Unknown(); got != hardFloor[fbQueryUnknown] {
|
||||
t.Errorf("Unknown = %q, want %q", got, hardFloor[fbQueryUnknown])
|
||||
}
|
||||
if got := fb.FromSources("два литра"); got != "вот что я нашла: два литра" {
|
||||
t.Errorf("FromSources = %q", got)
|
||||
}
|
||||
if got := fb.WorldGap(); got != hardFloor[fbWorldGap] {
|
||||
t.Errorf("WorldGap = %q", got)
|
||||
}
|
||||
}
|
||||
|
||||
// Hearing the identical words every time a request fails is how a failure stops
|
||||
// registering as one.
|
||||
func TestFallbacksDoNotRepeat(t *testing.T) {
|
||||
fb, err := LoadFallbacks(rand.NewSource(7))
|
||||
if err != nil {
|
||||
t.Fatalf("LoadFallbacks: %v", err)
|
||||
}
|
||||
prev := fb.Chat()
|
||||
for i := 0; i < 20; i++ {
|
||||
got := fb.Chat()
|
||||
if got == prev {
|
||||
t.Fatalf("chat repeated %q on turn %d", got, i)
|
||||
}
|
||||
prev = got
|
||||
}
|
||||
}
|
||||
|
||||
// The acknowledgements load, fill his words into the frame, and answer from the
|
||||
// floor when the file is gone.
|
||||
func TestAcksLoad(t *testing.T) {
|
||||
a, err := LoadAcks(rand.NewSource(1))
|
||||
if err != nil {
|
||||
t.Fatalf("LoadAcks: %v", err)
|
||||
}
|
||||
got := a.Say(AckFactValue, map[string]string{"key": "вода", "value": "2л"})
|
||||
if !strings.Contains(got, "вода") || !strings.Contains(got, "2л") {
|
||||
t.Errorf("Say(%s) = %q, want his key and value in it", AckFactValue, got)
|
||||
}
|
||||
var nilAcks *Acks
|
||||
if got := nilAcks.Say(AckNote, nil); got != ackFloor[AckNote] {
|
||||
t.Errorf("nil Acks said %q, want the floor %q", got, ackFloor[AckNote])
|
||||
}
|
||||
}
|
||||
@@ -5,6 +5,7 @@ import (
|
||||
"bytes"
|
||||
"context"
|
||||
"encoding/json"
|
||||
"errors"
|
||||
"fmt"
|
||||
"io"
|
||||
"log"
|
||||
@@ -26,6 +27,11 @@ import (
|
||||
|
||||
var listenRE = regexp.MustCompile(`listening on (https?://\S+)`)
|
||||
|
||||
// errEmptyResponse — the server answered and said nothing. Separate from a
|
||||
// transport failure: the model is up and produced no tokens, which is still not
|
||||
// an answer and must not score as one.
|
||||
var errEmptyResponse = errors.New("phraser: empty response from the model")
|
||||
|
||||
type LLMPhraser struct {
|
||||
cfg Config
|
||||
client *http.Client
|
||||
@@ -428,8 +434,11 @@ func (p *LLMPhraser) PhraseNudge(ctx context.Context, c loop.Candidate) (deliver
|
||||
}
|
||||
|
||||
// PhraseQuery prompts the LLM with the user's utterance and matching notes to
|
||||
// compose a natural answer. Falls back to "вот что я нашла: <notes>" on any
|
||||
// LLM error — better to give the raw data than silence.
|
||||
// compose a natural answer. On any LLM error it returns the fallback text —
|
||||
// "вот что я нашла: <notes>", or "не знаю." with no notes — and the error
|
||||
// together. The daemon uses the text and keeps the turn alive; a caller that is
|
||||
// measuring counts the failure. Until Vikunja #397 the error was dropped, so a
|
||||
// dead server scored as bad phrasing.
|
||||
func (p *LLMPhraser) PhraseQuery(ctx context.Context, utterance string, notes []string) (string, error) {
|
||||
// Blank sources are no sources. A caller that hands over one empty string —
|
||||
// a page that fetched to nothing, a snippet trimmed away — used to take the
|
||||
@@ -439,13 +448,15 @@ func (p *LLMPhraser) PhraseQuery(ctx context.Context, utterance string, notes []
|
||||
if len(notes) == 0 {
|
||||
sys, prompt := p.knowledgePrompt(utterance)
|
||||
resp, err := p.chatWithSystem(ctx, sys, prompt, 768)
|
||||
if err != nil || resp == "" {
|
||||
return "не знаю.", nil
|
||||
if err != nil {
|
||||
return UnknownFallback(), fmt.Errorf("phrase query (knowledge): %w", err)
|
||||
}
|
||||
if resp == "" {
|
||||
return UnknownFallback(), errEmptyResponse
|
||||
}
|
||||
text, _, perr := parseResponseMood(resp)
|
||||
if perr != nil {
|
||||
log.Printf("phraser: PhraseQuery: %v", perr)
|
||||
return "не знаю.", nil
|
||||
return UnknownFallback(), fmt.Errorf("phrase query (knowledge): %w", perr)
|
||||
}
|
||||
if text != "" {
|
||||
return text, nil
|
||||
@@ -457,13 +468,12 @@ func (p *LLMPhraser) PhraseQuery(ctx context.Context, utterance string, notes []
|
||||
text, _, perr := parseResponseMood(resp)
|
||||
if err != nil || perr != nil {
|
||||
// Read the notes out rather than ship a broken fragment.
|
||||
if perr != nil {
|
||||
log.Printf("phraser: PhraseQuery: %v", perr)
|
||||
cause := err
|
||||
if cause == nil {
|
||||
cause = perr
|
||||
}
|
||||
if len(notes) == 1 {
|
||||
return "вот что я нашла: " + notes[0], nil
|
||||
}
|
||||
return "вот что я нашла: " + strings.Join(notes, "; "), nil
|
||||
return SourcesFallback(strings.Join(notes, "; ")),
|
||||
fmt.Errorf("phrase query (evidence): %w", cause)
|
||||
}
|
||||
if text != "" {
|
||||
return text, nil
|
||||
@@ -472,8 +482,9 @@ func (p *LLMPhraser) PhraseQuery(ctx context.Context, utterance string, notes []
|
||||
}
|
||||
|
||||
// PhraseChat uses the LLM to respond conversationally, building a multi-turn
|
||||
// message array from dialogue history + the current user utterance. Falls back
|
||||
// to a simple greeting on any LLM error — better to say something than nothing.
|
||||
// message array from dialogue history + the current user utterance. On any LLM
|
||||
// error it returns both ChatFallback and the error, on the same rule as
|
||||
// PhraseQuery: the fallback keeps the turn alive, the error stays visible.
|
||||
func (p *LLMPhraser) PhraseChat(ctx context.Context, utterance string, history []dialogue.Turn) (string, error) {
|
||||
sys := chatSystemPrompt(p.cfg.ContextBlock)
|
||||
msgs := []chatMsg{
|
||||
@@ -490,13 +501,11 @@ func (p *LLMPhraser) PhraseChat(ctx context.Context, utterance string, history [
|
||||
|
||||
resp, err := p.chatWithMessages(ctx, msgs, 768)
|
||||
if err != nil {
|
||||
log.Printf("phraser: PhraseChat: %v", err)
|
||||
return "поговорили.", nil
|
||||
return ChatFallback(), fmt.Errorf("phrase chat: %w", err)
|
||||
}
|
||||
text, _, perr := parseResponseMood(resp)
|
||||
if perr != nil {
|
||||
log.Printf("phraser: PhraseChat: %v", perr)
|
||||
return "поговорили.", nil
|
||||
return ChatFallback(), fmt.Errorf("phrase chat: %w", perr)
|
||||
}
|
||||
if text != "" {
|
||||
return text, nil
|
||||
|
||||
@@ -70,18 +70,15 @@ func NewStub() *Stub { return &Stub{} }
|
||||
// prompted response from the model. The history parameter is accepted but
|
||||
// ignored at the stub level (the production impl uses it for multi-turn).
|
||||
func (s *Stub) PhraseChat(_ context.Context, _ string, _ []dialogue.Turn) (string, error) {
|
||||
return "поговорили.", nil
|
||||
return ChatFallback(), nil
|
||||
}
|
||||
|
||||
// PhraseQuery returns a deterministic summary of the best matching notes.
|
||||
func (s *Stub) PhraseQuery(_ context.Context, _ string, notes []string) (string, error) {
|
||||
if len(notes) == 0 {
|
||||
return "не знаю.", nil
|
||||
return UnknownFallback(), nil
|
||||
}
|
||||
if len(notes) == 1 {
|
||||
return "вот что я нашла: " + notes[0], nil
|
||||
}
|
||||
return "вот что я нашла: " + strings.Join(notes, "; "), nil
|
||||
return SourcesFallback(strings.Join(notes, "; ")), nil
|
||||
}
|
||||
|
||||
// Close implements Phraser.Close (no-op for the stub).
|
||||
|
||||
@@ -0,0 +1,112 @@
|
||||
// phraser/replier.go — reactive reply phrasing, the confirmation he hears
|
||||
// after every fact, note and reminder.
|
||||
//
|
||||
// It lived in cmd/mavend as package main until Vikunja #396, which meant the
|
||||
// most frequently heard sentence Maven says was the one path the phrasing eval
|
||||
// could not import, let alone score. Nothing here talks to the daemon: the
|
||||
// caller supplies the completer and the context block, and cmd/mavend keeps the
|
||||
// stub fallback so a model error still answers.
|
||||
package phraser
|
||||
|
||||
import (
|
||||
"context"
|
||||
"strings"
|
||||
"time"
|
||||
|
||||
"github.com/kami/maven/internal/llm"
|
||||
"github.com/kami/maven/internal/persona"
|
||||
"github.com/kami/maven/internal/router"
|
||||
)
|
||||
|
||||
// Completer is the model seam for the replier, a subset of router.Completer.
|
||||
// *llm.Client satisfies it.
|
||||
type Completer interface {
|
||||
Complete(ctx context.Context, r llm.Req) (string, error)
|
||||
}
|
||||
|
||||
// replyTimeout bounds one reply. Generous because the resident model on the CPU
|
||||
// floor is slow and the caller has a deterministic fallback anyway.
|
||||
const replyTimeout = 60 * time.Second
|
||||
|
||||
// ReplySystemPrompt — the reactive confirmation contract: one short Russian
|
||||
// sentence, feminine self-reference, informal address, no question.
|
||||
const ReplySystemPrompt = `Ты — Maven, домашняя ассистентка (о себе — в женском роде). Владелец — мужчина, говоришь с ним на "ты", в единственном числе; никогда не "вы"/"ваш" и не "он"/"его". Подтверди действие РОВНО ОДНИМ коротким предложением (≤120 символов), по-русски, спокойно и без официальных формулировок. Не задавай вопросов, не повторяй слова, не добавляй ничего после точки. Отвечай ТОЛЬКО одним объектом JSON с полями "response" (текст) и "mood" (ровно одно из: neutral, happy, thinking, tired, confused).
|
||||
Пример: {"response": "Записала, что ты выпил стакан воды.", "mood": "neutral"}
|
||||
Никогда не пиши "..." в поле response.`
|
||||
|
||||
// Replier phrases reactive confirmations with the resident model. It has no
|
||||
// fallback of its own: an error is returned, and the daemon answers from the
|
||||
// deterministic stub. That is also what makes it scorable — a dead server shows
|
||||
// up as an error rather than as bad phrasing.
|
||||
type Replier struct {
|
||||
c Completer
|
||||
|
||||
// block renders the shared context block per turn (who he is, the time).
|
||||
// nil ⇒ the prompt stands alone.
|
||||
block func() string
|
||||
}
|
||||
|
||||
// NewReplier builds a replier over c. block may be nil.
|
||||
func NewReplier(c Completer, block func() string) *Replier {
|
||||
return &Replier{c: c, block: block}
|
||||
}
|
||||
|
||||
// PhraseReply returns the confirmation for one decision. An empty string with a
|
||||
// nil error means the model produced nothing usable, which the caller must
|
||||
// treat exactly like an error.
|
||||
func (r *Replier) PhraseReply(ctx context.Context, d router.Decision) (string, error) {
|
||||
ctx, cancel := context.WithTimeout(ctx, replyTimeout)
|
||||
defer cancel()
|
||||
out, err := r.c.Complete(ctx, llm.Req{
|
||||
System: persona.Prepend(r.block, ReplySystemPrompt),
|
||||
User: replyContext(d),
|
||||
Grammar: ResponseGrammar,
|
||||
MaxTokens: 512,
|
||||
RepeatPenalty: 1.3,
|
||||
})
|
||||
if err != nil {
|
||||
return "", err
|
||||
}
|
||||
out = stripThink(out)
|
||||
if response, _, perr := parseResponseMood(out); perr != nil {
|
||||
return "", perr
|
||||
} else if response != "" {
|
||||
return response, nil
|
||||
}
|
||||
// fallback: the model answered in bare prose, which is fine here.
|
||||
return firstSentence(out), nil
|
||||
}
|
||||
|
||||
// firstSentence trims the model's output to a single clean confirmation: first
|
||||
// line, first sentence, whitespace-normalized — the last-line defense against a
|
||||
// small model that rambles past the first period despite the prompt + stop.
|
||||
func firstSentence(s string) string {
|
||||
s = strings.TrimSpace(s)
|
||||
if i := strings.IndexByte(s, '\n'); i >= 0 {
|
||||
s = s[:i]
|
||||
}
|
||||
// keep up to and including the first sentence-ending punctuation.
|
||||
if i := strings.IndexAny(s, ".!?"); i >= 0 {
|
||||
s = s[:i+1]
|
||||
}
|
||||
return strings.TrimSpace(s)
|
||||
}
|
||||
|
||||
// replyContext renders the decision into a compact RU description for the model.
|
||||
func replyContext(d router.Decision) string {
|
||||
switch d.Intent {
|
||||
case router.IntentFact:
|
||||
return "записала факт: " + d.Slots.Key + " " + d.Slots.Value
|
||||
case router.IntentNote:
|
||||
return "сохранила заметку: " + d.Slots.Text
|
||||
case router.IntentReminder:
|
||||
return "поставила напоминание: " + d.Slots.Text
|
||||
default:
|
||||
return string(d.Intent) + ": " + d.Slots.Text
|
||||
}
|
||||
}
|
||||
|
||||
// StripThink removes the <think> block a Thinking-variant model emits before its
|
||||
// answer. Exported for the daemon's own model callers, which parse output that
|
||||
// never passes through a phraser method.
|
||||
func StripThink(s string) string { return stripThink(s) }
|
||||
@@ -0,0 +1,90 @@
|
||||
package phraser
|
||||
|
||||
import (
|
||||
"context"
|
||||
"testing"
|
||||
|
||||
"github.com/kami/maven/internal/llm"
|
||||
"github.com/kami/maven/internal/router"
|
||||
)
|
||||
|
||||
type mockCompleter struct {
|
||||
out string
|
||||
err error
|
||||
}
|
||||
|
||||
func (m mockCompleter) Complete(_ context.Context, _ llm.Req) (string, error) { return m.out, m.err }
|
||||
|
||||
func TestReplierReturnsLLMReply(t *testing.T) {
|
||||
r := NewReplier(mockCompleter{out: `{"response":"записала, кофе закончился","mood":"neutral"}`}, nil)
|
||||
got, err := r.PhraseReply(context.Background(), noteDecision())
|
||||
if err != nil || got != "записала, кофе закончился" {
|
||||
t.Errorf("got %q, %v, want %q, nil", got, err, "записала, кофе закончился")
|
||||
}
|
||||
}
|
||||
|
||||
func TestReplierFallsBackToPlainText(t *testing.T) {
|
||||
r := NewReplier(mockCompleter{out: "записала, кофе закончился"}, nil)
|
||||
got, err := r.PhraseReply(context.Background(), noteDecision())
|
||||
if err != nil || got != "записала, кофе закончился" {
|
||||
t.Errorf("got %q, %v, want %q, nil", got, err, "записала, кофе закончился")
|
||||
}
|
||||
}
|
||||
|
||||
func TestReplierReportsTheModelError(t *testing.T) {
|
||||
r := NewReplier(mockCompleter{err: errTestLLMDown}, nil)
|
||||
got, err := r.PhraseReply(context.Background(), noteDecision())
|
||||
if err == nil {
|
||||
t.Errorf("got %q, nil error — a dead model must be reported, not phrased around", got)
|
||||
}
|
||||
}
|
||||
|
||||
// A fragment the grammar left half-open is a failed generation. It must come
|
||||
// back as an error so the daemon reaches its stub, not as a reply.
|
||||
func TestReplierRejectsBrokenJSON(t *testing.T) {
|
||||
r := NewReplier(mockCompleter{out: `{"response":"запис`}, nil)
|
||||
got, err := r.PhraseReply(context.Background(), noteDecision())
|
||||
if err == nil || got != "" {
|
||||
t.Errorf("got %q, %v, want empty and an error", got, err)
|
||||
}
|
||||
}
|
||||
|
||||
func TestReplierEmptyOutputIsEmpty(t *testing.T) {
|
||||
r := NewReplier(mockCompleter{out: ""}, nil)
|
||||
got, err := r.PhraseReply(context.Background(), noteDecision())
|
||||
if err != nil || got != "" {
|
||||
t.Errorf("got %q, %v, want empty and no error", got, err)
|
||||
}
|
||||
}
|
||||
|
||||
// grammarRecorder captures the request so the grammar can be asserted on.
|
||||
type grammarRecorder struct{ req llm.Req }
|
||||
|
||||
func (g *grammarRecorder) Complete(_ context.Context, r llm.Req) (string, error) {
|
||||
g.req = r
|
||||
return `{"response":"записала","mood":"neutral"}`, nil
|
||||
}
|
||||
|
||||
func TestReplierCarriesTheResponseGrammar(t *testing.T) {
|
||||
rec := &grammarRecorder{}
|
||||
r := NewReplier(rec, nil)
|
||||
if _, err := r.PhraseReply(context.Background(), noteDecision()); err != nil {
|
||||
t.Fatalf("PhraseReply: %v", err)
|
||||
}
|
||||
if rec.req.Grammar != ResponseGrammar {
|
||||
t.Errorf("grammar = %q, want ResponseGrammar", rec.req.Grammar)
|
||||
}
|
||||
if rec.req.System != ReplySystemPrompt {
|
||||
t.Errorf("system prompt = %q, want ReplySystemPrompt", rec.req.System)
|
||||
}
|
||||
}
|
||||
|
||||
func noteDecision() router.Decision {
|
||||
return router.Decision{Intent: router.IntentNote, Slots: router.Slots{Text: "кофе закончился"}}
|
||||
}
|
||||
|
||||
var errTestLLMDown = errTest("llm down")
|
||||
|
||||
type errTest string
|
||||
|
||||
func (e errTest) Error() string { return string(e) }
|
||||
@@ -215,10 +215,12 @@ func TestSwap_RollbackFailureLeavesNoBackendAndDegrades(t *testing.T) {
|
||||
if _, _, aerr := p.acquire(); !errors.Is(aerr, ErrNoBackend) {
|
||||
t.Errorf("acquire error = %v; want ErrNoBackend", aerr)
|
||||
}
|
||||
// Phrasing degrades to its fallback instead of failing the turn.
|
||||
// Phrasing degrades to its fallback instead of failing the turn, and since
|
||||
// Vikunja #397 it reports the error next to that fallback so a measuring
|
||||
// caller can tell "no model" from "bad phrasing".
|
||||
got, err := p.PhraseChat(context.Background(), "привет", nil)
|
||||
if err != nil {
|
||||
t.Fatalf("PhraseChat after a total failure returned an error: %v", err)
|
||||
if !errors.Is(err, ErrNoBackend) {
|
||||
t.Errorf("PhraseChat error = %v; want ErrNoBackend alongside the fallback", err)
|
||||
}
|
||||
if got == "" {
|
||||
t.Error("PhraseChat returned empty; the fallback must still say something")
|
||||
|
||||
+11
-11
@@ -25,7 +25,10 @@
|
||||
// the daemon seam (config wiring, no CoreAPI or voice-package change).
|
||||
package voice
|
||||
|
||||
import "github.com/kami/maven/internal/router"
|
||||
import (
|
||||
"github.com/kami/maven/internal/phraser"
|
||||
"github.com/kami/maven/internal/router"
|
||||
)
|
||||
|
||||
// Replier — the reactive reply phrasing seam. The daemon's reactive handler
|
||||
// calls Reply with the router's Decision; the impl produces a terse reply
|
||||
@@ -60,27 +63,24 @@ func (s *StubReplier) Reply(d router.Decision) string {
|
||||
if !d.Slots.HasFn {
|
||||
return "не могу это сделать — не разобрала действие."
|
||||
}
|
||||
return "ок, записала действие: " + d.Slots.Fn
|
||||
return phraser.Ack(phraser.AckAct, map[string]string{"fn": d.Slots.Fn})
|
||||
case router.IntentReminder:
|
||||
if d.Slots.HasTime {
|
||||
return "напомню."
|
||||
}
|
||||
return "напомню."
|
||||
return phraser.Ack(phraser.AckReminder, nil)
|
||||
case router.IntentFact:
|
||||
if d.Slots.HasKey {
|
||||
if d.Slots.Value != "" {
|
||||
return "отметила: " + d.Slots.Key + " = " + d.Slots.Value
|
||||
return phraser.Ack(phraser.AckFactValue, map[string]string{"key": d.Slots.Key, "value": d.Slots.Value})
|
||||
}
|
||||
return "отметила: " + d.Slots.Key
|
||||
return phraser.Ack(phraser.AckFactKey, map[string]string{"key": d.Slots.Key})
|
||||
}
|
||||
return "записала факт."
|
||||
return phraser.Ack(phraser.AckFact, nil)
|
||||
case router.IntentNote:
|
||||
return "сохранила заметку."
|
||||
return phraser.Ack(phraser.AckNote, nil)
|
||||
case router.IntentQuery:
|
||||
return "поискала в заметках — ничего не нашла."
|
||||
case router.IntentChat:
|
||||
return "поговорили." // stub — LLMReplier replaces this
|
||||
default:
|
||||
return "приняла."
|
||||
return phraser.Ack(phraser.AckGeneric, nil)
|
||||
}
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user