Report every address break, and stop -те verbs blinding the check

From a real reply in a nudge eval run: "Смотрите на его потребление
воды" is a plural imperative AND third person about him. Only the plural
printed.

Two separate faults. The check returned on its first hit, so the second
break stayed invisible and the failure read as milder than it was; it now
joins them. And "его" was not detected at all — looksVerb knows the
-й/-йте imperative but not the -те plural, so "смотрите" counted as the
person being talked about, which is what an antecedent means here.
pluralVerb already knows that form, so the antecedent test uses it too.

Third time a verb form has blinded this check. A fourth means it wants a
morphology table rather than another suffix.

Makefile

@@ -103,14 +103,17 @@ eval-router:
 eval-recall:
 	MAVEN_ONNX_LIB="$(MAVEN_ONNX_LIB)" $(GO) test -v -count=1 ./internal/memory/recalleval/
 
-# eval-phrasing -- score nudge phrasing (internal/phraser/eval). Verbose so the
+# eval-phrasing -- score nudge phrasing AND the conversational paths (chat,
+# query, general knowledge) in internal/phraser/eval. Verbose so the
 # report and every generated message land in the terminal. With no environment
 # it scores the deterministic Stub only, which is what CI runs. Set
 # MAVEN_LLM_URL to add the resident model:
 #   MAVEN_LLM_URL=http://127.0.0.1:18099 make eval-phrasing
-# The model run is slow (minutes) -- the timeout is raised to match.
+# The model run is slow (minutes) -- the timeout is raised to match. It covers
+# two fixtures now (15 nudges + 27 conversational cases, and the chat replies are
+# the long ones), hence 90m rather than 40m.
 eval-phrasing:
-	$(GO) test -v -count=1 -timeout 40m ./internal/phraser/eval/
+	$(GO) test -v -count=1 -timeout 90m ./internal/phraser/eval/
 
 # eval-models — score ONE llama-server against the same fixture, for the
 # resident-model bake-off (#278, #250). Start a server with the gguf you want,

internal/phraser/eval/address_multi_test.go

@@ -0,0 +1,33 @@
+package eval
+
+import (
+	"strings"
+	"testing"
+)
+
+// TestAddressReportsEveryBreak — the real reply from a nudge eval run broke in
+// two ways at once and the check named only the plural. Both must print: a
+// half-reported failure reads as a milder problem than it is.
+func TestAddressReportsEveryBreak(t *testing.T) {
+	body := "Смотрите на его потребление воды."
+	res := checkAddress(body)
+	if res.Pass {
+		t.Fatalf("checkAddress passed %q", body)
+	}
+	for _, want := range []string{"смотрите", "его"} {
+		if !strings.Contains(res.Detail, want) {
+			t.Errorf("detail %q does not name %q", res.Detail, want)
+		}
+	}
+}
+
+// One word repeated is one problem, so the detail must not say it twice.
+func TestAddressDeduplicates(t *testing.T) {
+	res := checkAddress("Вам стоит поесть, вам это нужно.")
+	if res.Pass {
+		t.Fatal("expected failure")
+	}
+	if n := strings.Count(res.Detail, "formal"); n != 1 {
+		t.Errorf("detail repeats the same break %d times: %q", n, res.Detail)
+	}
+}

internal/phraser/eval/checks.go

@@ -434,14 +434,26 @@ func looksVerb(w string) bool {
 func checkAddress(body string) Result {
 	words := addressWordRE.FindAllString(strings.ToLower(body), -1)
 
+	// Every break, not just the first. A bad reply usually breaks in more than
+	// one way at once — "Смотрите на его потребление воды" is a plural imperative
+	// AND third person about him — and reporting only the first hid the second,
+	// which made the failure look milder than it was.
+	var breaks []string
+	seen := map[string]bool{}
+	add := func(msg string) {
+		if seen[msg] {
+			return // the same word twice in one message is one problem, not two
+		}
+		seen[msg] = true
+		breaks = append(breaks, msg)
+	}
+
 	for i, w := range words {
 		if formalPronouns[w] {
-			return Result{CheckAddress, false,
-				fmt.Sprintf("formal %q — she says ты/тебя/тебе", w)}
+			add(fmt.Sprintf("formal %q — she says ты/тебя/тебе", w))
 		}
 		if pluralVerb(w) && !(i > 0 && prepositions[words[i-1]]) {
-			return Result{CheckAddress, false,
-				fmt.Sprintf("plural imperative %q — she uses the singular", w)}
+			add(fmt.Sprintf("plural imperative %q — she uses the singular", w))
 		}
 	}
 
@@ -455,17 +467,26 @@ func checkAddress(body string) Result {
 			if !unicode.Is(unicode.Cyrillic, []rune(p)[0]) && !isLatinWord(p) {
 				continue // punctuation
 			}
-			if notAnAntecedent[p] || prepositions[p] || thirdPersonHim[p] || looksVerb(p) {
+			// pluralVerb as well as looksVerb: looksVerb knows the imperative in
+			// -й/-йте but not the -те plural ("смотрите"), so "Смотрите на его
+			// потребление воды" counted "смотрите" as the person being talked
+			// about and the "его" never printed. Third time a verb form has
+			// blinded this check — if a fourth turns up, the antecedent test
+			// wants a real morphology table, not another suffix.
+			if notAnAntecedent[p] || prepositions[p] || thirdPersonHim[p] || looksVerb(p) || pluralVerb(p) {
 				continue
 			}
 			named = true
 			break
 		}
 		if !named {
-			return Result{CheckAddress, false,
-				fmt.Sprintf("third person %q with nobody else named — she talks to him, not about him", w)}
+			add(fmt.Sprintf("third person %q with nobody else named — she talks to him, not about him", w))
 		}
 	}
+
+	if len(breaks) > 0 {
+		return Result{CheckAddress, false, strings.Join(breaks, " + ")}
+	}
 	return Result{CheckAddress, true, ""}
 }
 
@@ -574,12 +595,47 @@ func checkCringe(body string) Result {
 // checkOnTopic — the message must name the thing the rule is about. A nudge
 // that never mentions water leaves the operator with a chime and no action.
 func checkOnTopic(c Case, body string) Result {
+	return checkOnTopicAny(c.WantAny, body)
+}
+
+// checkOnTopicAny is the same test over a bare want-list, so the talk scorer can
+// reuse it without owning a nudge Case.
+func checkOnTopicAny(wantAny []string, body string) Result {
 	low := strings.ToLower(body)
-	for _, want := range c.WantAny {
+	for _, want := range wantAny {
 		if strings.Contains(low, strings.ToLower(want)) {
 			return Result{CheckOnTopic, true, ""}
 		}
 	}
 	return Result{CheckOnTopic, false,
-		fmt.Sprintf("mentions none of %v", c.WantAny)}
+		fmt.Sprintf("mentions none of %v", wantAny)}
+}
+
+// --- shape checks for the free-form paths --------------------------------
+//
+// The nudge checks assume one short sentence. Chat and query replies are longer
+// by design, so the only shape worth testing there is that the model produced a
+// reply at all and did not trail off. Both are failure modes the fallbacks in
+// llmphraser.go hide: a truncated or empty generation still returns nil error.
+
+const (
+	CheckNonEmpty = "nonempty" // she said something
+	CheckEllipsis = "ellipsis" // she finished the sentence
+)
+
+func checkNonEmpty(body string) Result {
+	if strings.TrimSpace(body) == "" {
+		return Result{CheckNonEmpty, false, "empty reply"}
+	}
+	return Result{CheckNonEmpty, true, ""}
+}
+
+// checkEllipsis — a reply ending in "…" or "..." is a generation that ran out of
+// tokens, not a stylistic pause. Mid-sentence ellipses are left alone.
+func checkEllipsis(body string) Result {
+	trimmed := strings.TrimRight(strings.TrimSpace(body), `"'»)`)
+	if strings.HasSuffix(trimmed, "…") || strings.HasSuffix(trimmed, "...") {
+		return Result{CheckEllipsis, false, "reply trails off in an ellipsis — likely truncated"}
+	}
+	return Result{CheckEllipsis, true, ""}
 }

internal/phraser/eval/talk.go

@@ -0,0 +1,265 @@
+package eval
+
+// This file scores the CONVERSATIONAL paths, the ones the nudge fixture never
+// touches: chat, query-with-notes, and general knowledge. All three now carry
+// the shared persona block (internal/persona), and all three produce long
+// free-form Russian — which is exactly where a persona break (formality, third
+// person, masculine self-reference) is most likely and where, until this file,
+// nothing could see one.
+//
+// Why a second fixture instead of more nudge cases: the checks differ. A nudge
+// must be one short sentence with no question in it; a chat reply is allowed
+// 1-3 sentences and a follow-up question is a FEATURE there. Mixing them would
+// need per-case check masks, and the nudge scorer stays untouched this way.
+//
+// Why per-path reporting: a chat regression and a knowledge regression have
+// different causes (chat prompt vs router.KnowledgePrompt), and one blended
+// percentage cannot tell them apart.
+
+import (
+	"context"
+	_ "embed"
+	"encoding/json"
+	"fmt"
+	"sort"
+	"strings"
+	"time"
+
+	"github.com/kami/maven/internal/dialogue"
+)
+
+//go:embed talk_v1.json
+var talkFixtureJSON []byte
+
+// The three 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
+)
+
+// TalkPaths — report order.
+var TalkPaths = []string{PathChat, PathQuery, PathKnowledge}
+
+// 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
+// properties and would fail a correct chat reply. These paths return no mood at
+// all, so there is nothing to check there.
+var TalkCheckNames = []string{
+	CheckNonEmpty, CheckEllipsis, CheckLang, CheckFeminine, CheckAddress, CheckOnTopic,
+}
+
+// TalkCase — one turn as the daemon would present it.
+//
+// History is flat text because that is all PhraseChat uses (it concatenates
+// turn texts into one user message); intents and slots would be dead fields.
+// Notes are what the store would have matched for a query.
+//
+// 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.
+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"`
+	WantAny   []string `json:"want_any"`
+	Tags      []string `json:"tags,omitempty"`
+	Note      string   `json:"note,omitempty"`
+}
+
+// TalkFixture — the versioned envelope, same gating as Fixture.
+type TalkFixture struct {
+	SchemaVersion int        `json:"schema_version"`
+	Name          string     `json:"name"`
+	Notes         []string   `json:"notes"`
+	Cases         []TalkCase `json:"cases"`
+}
+
+// LoadTalk returns the embedded conversational fixture.
+func LoadTalk() (TalkFixture, error) {
+	var f TalkFixture
+	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 len(f.Cases) == 0 {
+		return TalkFixture{}, fmt.Errorf("talk fixture has no cases")
+	}
+	return f, nil
+}
+
+// Talker — the two methods a conversational path must have to be scorable.
+// *phraser.LLMPhraser satisfies it; same trick as Nudger.
+type Talker interface {
+	PhraseChat(ctx context.Context, utterance string, history []dialogue.Turn) (string, error)
+	PhraseQuery(ctx context.Context, utterance string, notes []string) (string, error)
+}
+
+// TalkOutcome — one scored case.
+type TalkOutcome struct {
+	Case    TalkCase
+	Reply   string
+	Err     error
+	Latency time.Duration
+	Pass    bool
+	Failed  []string
+	Reasons []string
+}
+
+// TalkReport — the aggregate. ByPath is the point of this scorer.
+type TalkReport struct {
+	Name     string
+	Total    int
+	Passed   int
+	Errors   int
+	ByCheck  map[string]int
+	ByPath   map[string]TagStat
+	Outcomes []TalkOutcome
+	P50      time.Duration
+	P95      time.Duration
+	Max      time.Duration
+}
+
+// Accuracy — fraction of cases that passed every check.
+func (r TalkReport) Accuracy() float64 {
+	if r.Total == 0 {
+		return 0
+	}
+	return float64(r.Passed) / float64(r.Total)
+}
+
+// ScoreTalk runs every case through t and aggregates. A phrasing error scores as
+// a miss and is counted separately: "the model was down" and "the model wrote
+// something bad" must not be the same number.
+func ScoreTalk(ctx context.Context, name string, t Talker, f TalkFixture) (TalkReport, error) {
+	rep := TalkReport{
+		Name:    name,
+		Total:   len(f.Cases),
+		ByCheck: map[string]int{},
+		ByPath:  map[string]TagStat{},
+	}
+	for _, n := range TalkCheckNames {
+		rep.ByCheck[n] = 0
+	}
+	lat := make([]time.Duration, 0, len(f.Cases))
+
+	for _, c := range f.Cases {
+		start := time.Now()
+		reply, err := c.run(ctx, t)
+		o := TalkOutcome{Case: c, Reply: reply, Err: err, Latency: time.Since(start)}
+		lat = append(lat, o.Latency)
+
+		if err != nil {
+			rep.Errors++
+			o.Failed = append(o.Failed, "call")
+			o.Reasons = append(o.Reasons, fmt.Sprintf("phrase error: %v", err))
+		} else {
+			for _, res := range RunTalkChecks(c, reply) {
+				if res.Pass {
+					rep.ByCheck[res.Name]++
+					continue
+				}
+				o.Failed = append(o.Failed, res.Name)
+				o.Reasons = append(o.Reasons, res.Name+": "+res.Detail)
+			}
+		}
+
+		o.Pass = len(o.Failed) == 0
+		if o.Pass {
+			rep.Passed++
+		}
+		bump(rep.ByPath, c.Path, o.Pass)
+		rep.Outcomes = append(rep.Outcomes, o)
+	}
+
+	sort.Slice(lat, func(i, j int) bool { return lat[i] < lat[j] })
+	rep.P50, rep.P95 = percentile(lat, 0.50), percentile(lat, 0.95)
+	if len(lat) > 0 {
+		rep.Max = lat[len(lat)-1]
+	}
+	return rep, nil
+}
+
+// run dispatches the case to its path. knowledge and query are the same method;
+// the empty notes slice is what selects the no-notes branch inside PhraseQuery.
+func (c TalkCase) run(ctx context.Context, t Talker) (string, error) {
+	switch c.Path {
+	case PathChat:
+		return t.PhraseChat(ctx, c.Utterance, c.turns())
+	case PathQuery:
+		return t.PhraseQuery(ctx, c.Utterance, c.Notes)
+	case PathKnowledge:
+		return t.PhraseQuery(ctx, c.Utterance, nil)
+	}
+	return "", fmt.Errorf("unknown path %q", c.Path)
+}
+
+func (c TalkCase) turns() []dialogue.Turn {
+	turns := make([]dialogue.Turn, 0, len(c.History))
+	for _, h := range c.History {
+		turns = append(turns, dialogue.Turn{Text: h})
+	}
+	return turns
+}
+
+// RunTalkChecks scores one reply. Order matches TalkCheckNames.
+func RunTalkChecks(c TalkCase, reply string) []Result {
+	return []Result{
+		checkNonEmpty(reply),
+		checkEllipsis(reply),
+		checkLang(reply),
+		checkFeminine(reply),
+		checkAddress(reply),
+		checkOnTopicAny(c.WantAny, reply),
+	}
+}
+
+// String renders the comparison table — composite, then per-check so a
+// regression names the property, then per-path so it names the prompt.
+func (r TalkReport) String() string {
+	var b strings.Builder
+	fmt.Fprintf(&b, "%s: %d/%d cases pass every check (%.1f%%), %d errors\n",
+		r.Name, r.Passed, r.Total, 100*r.Accuracy(), r.Errors)
+	for _, name := range TalkCheckNames {
+		fmt.Fprintf(&b, "  %-10s %d/%d\n", name, r.ByCheck[name], r.Total)
+	}
+	fmt.Fprintf(&b, "  latency: p50 %s  p95 %s  max %s\n", r.P50, r.P95, r.Max)
+	fmt.Fprintf(&b, "  by path: %s\n", renderStats(r.ByPath))
+	return b.String()
+}
+
+// Failures — per-case detail, sorted by ID so two runs diff cleanly.
+func (r TalkReport) Failures() string {
+	var b strings.Builder
+	for _, o := range r.sorted() {
+		if o.Pass {
+			continue
+		}
+		fmt.Fprintf(&b, "  %s %q\n    %s\n", o.Case.ID, o.Reply, strings.Join(o.Reasons, "; "))
+	}
+	return b.String()
+}
+
+// Replies — every generated reply verbatim. This is what a human reads to judge
+// tone; the score only says which checks fired.
+func (r TalkReport) Replies() string {
+	var b strings.Builder
+	for _, o := range r.sorted() {
+		mark := "ok  "
+		if !o.Pass {
+			mark = "FAIL"
+		}
+		fmt.Fprintf(&b, "  %s %-9s %-22s %q\n", mark, o.Case.Path, o.Case.ID, o.Reply)
+	}
+	return b.String()
+}
+
+func (r TalkReport) sorted() []TalkOutcome {
+	out := append([]TalkOutcome(nil), r.Outcomes...)
+	sort.Slice(out, func(i, j int) bool { return out[i].Case.ID < out[j].Case.ID })
+	return out
+}

internal/phraser/eval/talk_test.go

@@ -0,0 +1,163 @@
+package eval
+
+import (
+	"context"
+	"os"
+	"strings"
+	"testing"
+	"time"
+
+	"github.com/kami/maven/internal/dialogue"
+	"github.com/kami/maven/internal/llm"
+	"github.com/kami/maven/internal/persona"
+	"github.com/kami/maven/internal/phraser"
+)
+
+// perPathMinimum — the resolution floor. A per-path score built on a handful of
+// cases moves by 12% when a single reply changes, which cannot distinguish a
+// prompt regression from noise.
+const perPathMinimum = 8
+
+// TestTalkFixture — the fixture itself has to be sound before any score off it
+// means anything.
+func TestTalkFixture(t *testing.T) {
+	f, err := LoadTalk()
+	if err != nil {
+		t.Fatalf("LoadTalk: %v", err)
+	}
+
+	seen := map[string]bool{}
+	byPath := map[string]int{}
+	for _, c := range f.Cases {
+		if seen[c.ID] {
+			t.Errorf("duplicate case id %q", c.ID)
+		}
+		seen[c.ID] = true
+
+		switch c.Path {
+		case PathChat, PathQuery, PathKnowledge:
+		default:
+			t.Errorf("%s: unknown path %q", c.ID, c.Path)
+		}
+		byPath[c.Path]++
+
+		if strings.TrimSpace(c.Utterance) == "" {
+			t.Errorf("%s: empty utterance", c.ID)
+		}
+		if len(c.WantAny) == 0 {
+			t.Errorf("%s: no want_any — the reply cannot be checked for topic", c.ID)
+		}
+		// A query case with no notes would silently score the knowledge path.
+		if c.Path == PathQuery && len(c.Notes) == 0 {
+			t.Errorf("%s: query case has no notes", c.ID)
+		}
+		if c.Path == PathKnowledge && len(c.Notes) > 0 {
+			t.Errorf("%s: knowledge case must have no notes", c.ID)
+		}
+	}
+
+	for _, p := range TalkPaths {
+		if byPath[p] < perPathMinimum {
+			t.Errorf("path %s has %d cases, want at least %d", p, byPath[p], perPathMinimum)
+		}
+	}
+}
+
+// fakeTalker — a scripted Talker, so the scorer is testable without a model.
+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
+}
+
+// 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) {
+	f, err := LoadTalk()
+	if err != nil {
+		t.Fatalf("LoadTalk: %v", err)
+	}
+	// Formal address, off-topic, trailing ellipsis: three checks fail at once.
+	rep, err := ScoreTalk(context.Background(), "fake", fakeTalker{"Приходите, я вас жду…"}, f)
+	if err != nil {
+		t.Fatalf("ScoreTalk: %v", err)
+	}
+	if rep.Total != len(f.Cases) || rep.Passed != 0 {
+		t.Errorf("got %d/%d passing, want 0/%d", rep.Passed, rep.Total, len(f.Cases))
+	}
+	if rep.ByCheck[CheckAddress] != 0 {
+		t.Errorf("formal reply passed the address check %d times", rep.ByCheck[CheckAddress])
+	}
+	if rep.ByCheck[CheckEllipsis] != 0 {
+		t.Errorf("truncated reply passed the ellipsis check %d times", rep.ByCheck[CheckEllipsis])
+	}
+	for _, p := range TalkPaths {
+		if rep.ByPath[p].Total == 0 {
+			t.Errorf("path %s missing from the report", p)
+		}
+	}
+	if !strings.Contains(rep.String(), "by path") {
+		t.Error("report does not break down by path")
+	}
+}
+
+// TestLLMTalkBaseline — the resident model on the three conversational paths.
+// Opt-in exactly like TestLLMPhrasingBaseline: CI has no model and a run costs
+// minutes on the CPU target.
+//
+//	MAVEN_LLM_URL=http://127.0.0.1:18099 \
+//	  go test -run TestLLMTalkBaseline ./internal/phraser/eval/
+//
+// Reports, does not assert a quality bar — the numbers are the input to tuning
+// the persona prompt. The one thing worth failing on is a harness fault.
+func TestLLMTalkBaseline(t *testing.T) {
+	base := os.Getenv("MAVEN_LLM_URL")
+	if base == "" {
+		t.Skip("MAVEN_LLM_URL unset — point it at a running llama-server (see doc comment)")
+	}
+	noProxyLoopback(t)
+
+	ctx := context.Background()
+	f, err := LoadTalk()
+	if err != nil {
+		t.Fatalf("LoadTalk: %v", err)
+	}
+
+	cfg := phraser.DefaultConfig("")
+	cfg.Timeout = 5 * time.Minute
+	cfg.ContextBlock = func() string { return persona.Facts{}.Block(time.Now()) }
+	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).
+	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.Logf("scoring model %s at %s", model, base)
+
+	rep, err := ScoreTalk(ctx, "llm ("+model+", built-in persona)", p, 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)
+	}
+}

internal/phraser/eval/talk_v1.json

@@ -0,0 +1,227 @@
+{
+  "schema_version": 1,
+  "name": "ru-talk-v1",
+  "notes": [
+    "Scores the three conversational phrasing paths: chat (PhraseChat), query (PhraseQuery with notes) and knowledge (PhraseQuery with no notes). The nudge fixture does not cover any of them.",
+    "Nine cases per path, not five. The nudge fixture is 15 sampled cases and cannot resolve a change smaller than ~3 cases; a per-path score off five cases would be worse still. More cases per path is the point of this fixture.",
+    "The owner is a man, addressed informally as ty, living alone with a home server. Every utterance is written the way he actually talks to her.",
+    "chat-formality-bait and chat-about-me exist to provoke the two persona breaks the nudge eval caught: the formal vy/vas plural, and talking about him in the third person.",
+    "want_any fragments are stems so Russian declension does not defeat the on-topic check. They are lowercased before comparison.",
+    "want_any is a plain substring test, so a fragment that is too short passes by accident: \"ты\" matches inside \"работы\", \"нет\" inside \"интернет\". Keep every fragment to three or more letters of a real stem.",
+    "Notes are written as the store would have them: short, first person, no punctuation discipline."
+  ],
+  "cases": [
+    {
+      "id": "chat-how-are-you",
+      "path": "chat",
+      "utterance": "привет, как дела?",
+      "want_any": ["норм", "хорош", "порядк", "тут", "работ"],
+      "tags": ["greeting"],
+      "note": "The plainest chat turn there is. If the persona breaks anywhere it breaks here first."
+    },
+    {
+      "id": "chat-formality-bait",
+      "path": "chat",
+      "utterance": "не могли бы вы подсказать, чем вы сейчас занимаетесь?",
+      "want_any": ["сейчас", "ничем", "ничего", "жду", "тут"],
+      "tags": ["persona-bait", "address"],
+      "note": "Deliberately polite and plural. A small model mirrors the register and answers with vy/vas — the exact break the address check was written for."
+    },
+    {
+      "id": "chat-about-me",
+      "path": "chat",
+      "utterance": "расскажи обо мне",
+      "want_any": ["теб"],
+      "tags": ["persona-bait", "third-person"],
+      "note": "Baits the third person: she should say 'ты живёшь один', not 'он живёт один', as if reporting to somebody else."
+    },
+    {
+      "id": "chat-bored-evening",
+      "path": "chat",
+      "utterance": "скучно что-то вечером, посоветуй чем заняться",
+      "want_any": ["можеш", "попробу", "почита", "прогул", "фильм", "серв"],
+      "tags": ["open-ended"]
+    },
+    {
+      "id": "chat-followup-server",
+      "path": "chat",
+      "utterance": "а стоит его вообще перезагружать?",
+      "history": ["сервер опять шумит как самолёт", "похоже вентилятор"],
+      "want_any": ["серв", "перезагру", "вентил", "шум"],
+      "tags": ["history", "anaphora"],
+      "note": "The pronoun 'его' only resolves through history. Also the one case where 'он' about the server is legitimate."
+    },
+    {
+      "id": "chat-tired",
+      "path": "chat",
+      "utterance": "устал я сегодня, весь день за компом",
+      "want_any": ["отдохн", "устал", "перерыв", "спат", "день"],
+      "tags": ["tone"],
+      "note": "Invites the fake-concern and emotional-support drift; the reply should stay plain."
+    },
+    {
+      "id": "chat-thanks",
+      "path": "chat",
+      "utterance": "спасибо, выручила",
+      "want_any": ["пожалуйст", "не за что", "рада", "обращ"],
+      "tags": ["persona", "feminine"],
+      "note": "Feminine self-reference is unavoidable in an answer to thanks: 'рада', not 'рад'."
+    },
+    {
+      "id": "chat-what-can-you-do",
+      "path": "chat",
+      "utterance": "что ты вообще умеешь?",
+      "want_any": ["напомн", "замет", "запис", "могу", "умею"],
+      "tags": ["self-description", "feminine"]
+    },
+    {
+      "id": "chat-joke",
+      "path": "chat",
+      "utterance": "расскажи что-нибудь смешное",
+      "want_any": ["анекдот", "шутк", "смешн", "истори"],
+      "tags": ["open-ended"],
+      "note": "Longest free-form generation in the chat set — the most likely place for a truncated reply."
+    },
+    {
+      "id": "query-router-password",
+      "path": "query",
+      "utterance": "что я записывал про пароль от роутера?",
+      "notes": ["пароль от роутера admin/xxK9tp — на наклейке снизу", "роутер висит в коридоре"],
+      "want_any": ["парол", "роутер", "наклейк"],
+      "tags": ["notes", "recall"]
+    },
+    {
+      "id": "query-bedtime-yesterday",
+      "path": "query",
+      "utterance": "напомни, во сколько я вчера лёг?",
+      "notes": ["лёг спать в 02:40", "сегодня встал в 9"],
+      "want_any": ["02:40", "2:40", "полтрет", "ноч"],
+      "tags": ["notes", "time"]
+    },
+    {
+      "id": "query-doctor-name",
+      "path": "query",
+      "utterance": "как звали того стоматолога, которого мне советовали?",
+      "notes": ["стоматолог Игорь Валерьевич, клиника на Ленина, советовал Дима"],
+      "want_any": ["игор", "валерьев", "стоматолог"],
+      "tags": ["notes", "recall"]
+    },
+    {
+      "id": "query-disk-plan",
+      "path": "query",
+      "utterance": "я что-то планировал с диском на сервере, что именно?",
+      "notes": ["купить второй hdd на 4тб под бэкапы", "перенести медиатеку с системного диска"],
+      "want_any": ["hdd", "бэкап", "диск", "4тб", "медиатек"],
+      "tags": ["notes", "homeserver"]
+    },
+    {
+      "id": "query-notes-do-not-answer",
+      "path": "query",
+      "utterance": "сколько я заплатил за домен?",
+      "notes": ["домен продлевается в марте", "хостинг оплачен на год вперёд"],
+      "want_any": ["домен", "не зна", "не указ"],
+      "tags": ["notes", "negative"],
+      "note": "The notes do not contain the price. The prompt tells her to say so; a made-up number is the failure being watched for."
+    },
+    {
+      "id": "query-single-note",
+      "path": "query",
+      "utterance": "где лежит запасной ключ?",
+      "notes": ["запасной ключ у соседа с четвёртого этажа"],
+      "want_any": ["ключ", "сосед", "четверт"],
+      "tags": ["notes", "single"],
+      "note": "One note only — PhraseQuery has a separate branch for len(notes) == 1."
+    },
+    {
+      "id": "query-polite-form",
+      "path": "query",
+      "utterance": "подскажите, пожалуйста, что у меня записано по машине?",
+      "notes": ["замена масла на 92 тысячах", "страховка до 14 сентября"],
+      "want_any": ["масл", "страховк", "92", "сентябр"],
+      "tags": ["notes", "persona-bait", "address"],
+      "note": "Polite plural in the question. The answer must still be ty."
+    },
+    {
+      "id": "query-shopping",
+      "path": "query",
+      "utterance": "что мне надо было купить?",
+      "notes": ["купить кофе и фильтры", "закончилась паста"],
+      "want_any": ["кофе", "фильтр", "паст"],
+      "tags": ["notes", "list"]
+    },
+    {
+      "id": "query-wifi-guest",
+      "path": "query",
+      "utterance": "я записывал гостевой вайфай?",
+      "notes": ["гостевая сеть maven-guest, пароль 12345678 меняю раз в месяц"],
+      "want_any": ["guest", "гостев", "12345678", "парол"],
+      "tags": ["notes", "recall"]
+    },
+    {
+      "id": "know-sky-blue",
+      "path": "knowledge",
+      "utterance": "почему небо синее?",
+      "want_any": ["све", "рассеи", "атмосфер", "син", "волн"],
+      "tags": ["general"]
+    },
+    {
+      "id": "know-boil-egg",
+      "path": "knowledge",
+      "utterance": "сколько варить яйцо вкрутую?",
+      "want_any": ["минут", "8", "9", "10", "варит"],
+      "tags": ["general", "practical"]
+    },
+    {
+      "id": "know-ssd-vs-hdd",
+      "path": "knowledge",
+      "utterance": "чем ssd отличается от hdd?",
+      "want_any": ["ssd", "hdd", "быстр", "диск", "механич"],
+      "tags": ["general", "tech"]
+    },
+    {
+      "id": "know-cat-purr",
+      "path": "knowledge",
+      "utterance": "почему кошки мурчат?",
+      "want_any": ["кош", "мурч", "вибра", "успока"],
+      "tags": ["general"]
+    },
+    {
+      "id": "know-hiccups",
+      "path": "knowledge",
+      "utterance": "как быстро избавиться от икоты?",
+      "want_any": ["икот", "дыха", "вод", "задерж"],
+      "tags": ["general", "practical"]
+    },
+    {
+      "id": "know-polite-form",
+      "path": "knowledge",
+      "utterance": "не могли бы вы объяснить, что такое vpn?",
+      "want_any": ["vpn", "туннел", "трафик", "сет", "шифр"],
+      "tags": ["general", "persona-bait", "address"],
+      "note": "Polite plural bait on the knowledge prompt, which is a different system prompt from chat and must hold the same line."
+    },
+    {
+      "id": "know-dont-know",
+      "path": "knowledge",
+      "utterance": "как зовут моего соседа снизу?",
+      "want_any": ["не зна", "не мог"],
+      "tags": ["general", "negative"],
+      "note": "Unanswerable without notes. Admitting it beats inventing a name; watching for the invention."
+    },
+    {
+      "id": "know-water-per-day",
+      "path": "knowledge",
+      "utterance": "сколько воды в день надо пить?",
+      "want_any": ["вод", "литр", "стакан", "пит"],
+      "tags": ["general", "health"],
+      "note": "Overlaps a nudge rule on purpose: the knowledge answer must not turn into a nudge."
+    },
+    {
+      "id": "know-thunder-delay",
+      "path": "knowledge",
+      "utterance": "почему гром слышно позже молнии?",
+      "want_any": ["звук", "све", "быстр", "гром", "молни"],
+      "tags": ["general"]
+    }
+  ]
+}