Merge commit '94eb92f' into overnight-jul31

# Conflicts:
#	Makefile

Makefile

@@ -16,7 +16,7 @@ PIPER_BIN     := $(shell pwd)/deps/piper/piper
 PIPER_MODEL   := $(shell pwd)/models/tts/ru_RU-irina-medium.onnx
 PIPER_ESPEAK  := $(shell pwd)/deps/piper/espeak-ng-data
 
-.PHONY: all build build-stt build-tts build-daemon build-client build-waked build-web build-poll build-caldav clean test fmt-check vet run-stt run-tts run-web download-embedder deps-go eval-router eval-recall
+.PHONY: all build build-stt build-tts build-daemon build-client build-waked build-web build-poll build-caldav clean test fmt-check vet run-stt run-tts run-web download-embedder deps-go eval-router eval-recall eval-phrasing eval-models
 
 all: build
 
@@ -103,6 +103,30 @@ 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
+# 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.
+eval-phrasing:
+	$(GO) test -v -count=1 -timeout 40m ./internal/phraser/eval/
+
+# eval-models — score ONE llama-server against the same fixture, for the
+# resident-model bake-off (#278, #250). Start a server with the gguf you want,
+# then:
+#
+#   make eval-models MAVEN_LLM_URL=http://127.0.0.1:18100
+#
+# The report names carry the model llama-server reports, so runs from two
+# checkpoints stay apart. Only the LLM test runs — the classifier baselines do
+# not depend on the model and take the ONNX runtime with them.
+MAVEN_LLM_URL ?= http://127.0.0.1:18099
+
+eval-models:
+	MAVEN_LLM_URL="$(MAVEN_LLM_URL)" $(GO) test -v -count=1 -timeout 60m \
+		-run TestLLMRouterBaseline ./internal/router/eval/
+
 run-stt: build-stt
 	LD_LIBRARY_PATH="$(shell pwd)/deps/lib" \
 		./mavsttd -socket /tmp/maven/stt.sock -model $(WHISPER_MODEL)

internal/phraser/eval/checks.go

@@ -0,0 +1,287 @@
+package eval
+
+import (
+	"fmt"
+	"regexp"
+	"strings"
+	"unicode"
+	"unicode/utf8"
+)
+
+// The check names, in report order. Every check is a string or length test — no
+// model grades another model here.
+const (
+	CheckMood     = "mood"     // mood is in the documented enum
+	CheckLang     = "lang"     // the operator's language, not the prompt's
+	CheckLength   = "length"   // a nudge is one sentence, not a paragraph
+	CheckFeminine = "feminine" // her self-reference is feminine (hard constraint)
+	CheckCringe   = "cringe"   // DESIGN.md § Non-goals, "not a relationship"
+	CheckOnTopic  = "ontopic"  // says the thing the rule is about
+)
+
+// CheckNames — report order.
+var CheckNames = []string{CheckMood, CheckLang, CheckLength, CheckFeminine, CheckCringe, CheckOnTopic}
+
+// Result — one check on one message.
+type Result struct {
+	Name   string
+	Pass   bool
+	Detail string
+}
+
+// Moods — the fixed enum from the LLM output contract. Not extended here; the
+// contract lives in the daemon and the harness only reads it.
+var Moods = map[string]bool{
+	"neutral": true, "happy": true, "thinking": true, "tired": true, "confused": true,
+}
+
+// Length ceilings. Justification: the nudge is spoken by piper at roughly 14
+// characters per second, so 120 characters is about 8 seconds of speech. The
+// operator has AuDHD — past one short sentence a nudge stops being a nudge and
+// becomes something to tune out, which is exactly the "not a nag" failure. The
+// word ceiling catches the same thing for languages that pack more per byte.
+const (
+	MaxChars = 120
+	MaxWords = 16
+)
+
+// RunChecks scores one message. Order matches CheckNames.
+func RunChecks(c Case, body, mood string) []Result {
+	return []Result{
+		checkMood(mood),
+		checkLang(body),
+		checkLength(body),
+		checkFeminine(body),
+		checkCringe(body),
+		checkOnTopic(c, body),
+	}
+}
+
+func checkMood(mood string) Result {
+	if Moods[mood] {
+		return Result{CheckMood, true, ""}
+	}
+	return Result{CheckMood, false, fmt.Sprintf("mood %q not in the enum", mood)}
+}
+
+// checkLang — the operator is Russian-speaking and the nudge is spoken aloud by
+// a Russian piper voice. An English nudge is not a tone problem, it is an
+// unusable one.
+func checkLang(body string) Result {
+	cyr, lat := 0, 0
+	for _, r := range body {
+		switch {
+		case unicode.Is(unicode.Cyrillic, r):
+			cyr++
+		case r >= 'a' && r <= 'z', r >= 'A' && r <= 'Z':
+			lat++
+		}
+	}
+	if cyr > lat {
+		return Result{CheckLang, true, ""}
+	}
+	return Result{CheckLang, false, fmt.Sprintf("not Russian (%d cyrillic vs %d latin letters)", cyr, lat)}
+}
+
+func checkLength(body string) Result {
+	chars := utf8.RuneCountInString(body)
+	words := len(strings.Fields(body))
+	if chars <= MaxChars && words <= MaxWords {
+		return Result{CheckLength, true, ""}
+	}
+	return Result{CheckLength, false,
+		fmt.Sprintf("%d chars / %d words, ceiling %d / %d", chars, words, MaxChars, MaxWords)}
+}
+
+// --- feminine self-reference ---------------------------------------------
+//
+// The hard constraint (CLAUDE.md, DESIGN.md § Identity): Maven's Russian
+// self-reference is feminine. The operator is male, so second-person forms
+// addressed to him are MASCULINE and must not be flagged — "ты не пил воду" is
+// correct, "я напомнил" is not. Both directions matter, which is why this is a
+// windowed scan around "я" and not a bare search for masculine endings.
+
+var wordRE = regexp.MustCompile(`[\p{Cyrillic}]+|[,.;:!?…—-]`)
+
+// secondPerson — pronouns that end the self-reference window. Everything after
+// one of these is about him, not about her.
+var secondPerson = map[string]bool{
+	"ты": true, "тебе": true, "тебя": true, "тобой": true,
+	"вы": true, "вам": true, "вас": true,
+	"он": true, "она": true, "оно": true, "они": true,
+}
+
+// masculinePredicative — short adjectives with no verb ending to key off.
+var masculinePredicative = map[string]bool{
+	"должен": true, "готов": true, "рад": true, "уверен": true,
+	"обязан": true, "сам": true, "занят": true, "прав": true,
+}
+
+// nounsEndingInL — the false positives of "ends in л ⇒ masculine past tense".
+// Small on purpose: it only has to cover nouns a nudge might actually use.
+var nounsEndingInL = map[string]bool{
+	"стол": true, "стул": true, "пол": true, "зал": true, "гол": true,
+	"узел": true, "отдел": true, "файл": true, "канал": true, "угол": true,
+	"футбол": true, "вокзал": true, "металл": true, "интервал": true,
+	"уровень": true, "мускул": true, "апрель": true, "июль": true, "рубль": true,
+}
+
+// masculinePast reports whether a word looks like a masculine past-tense verb.
+// Russian past tense is gendered by suffix: -л (m), -ла (f). A 0.8B with weak
+// Russian defaults to the masculine form, which is the exact drift being
+// measured.
+func masculinePast(w string) bool {
+	if len([]rune(w)) < 3 || nounsEndingInL[w] {
+		return false
+	}
+	return strings.HasSuffix(w, "л") || strings.HasSuffix(w, "лся")
+}
+
+func checkFeminine(body string) Result {
+	words := wordRE.FindAllString(strings.ToLower(body), -1)
+	for i, w := range words {
+		if w != "я" {
+			continue
+		}
+		// Scan the next few words. Stop at punctuation or at a second-person
+		// pronoun: past that point the sentence is about him and masculine is
+		// correct.
+		for j := i + 1; j < len(words) && j <= i+3; j++ {
+			nw := words[j]
+			if len(nw) == 1 && !unicode.Is(unicode.Cyrillic, []rune(nw)[0]) {
+				break
+			}
+			if secondPerson[nw] {
+				break
+			}
+			if masculinePast(nw) || masculinePredicative[nw] {
+				return Result{CheckFeminine, false,
+					fmt.Sprintf("masculine self-reference %q after \"я\"", nw)}
+			}
+		}
+	}
+	// Second pass: self-reference with the pronoun dropped — "напомнил тебе",
+	// "проверил за тебя". A masculine past-tense verb whose object is HIM can
+	// only be her speaking about herself.
+	for i, w := range words {
+		if !masculinePast(w) || i+1 >= len(words) {
+			continue
+		}
+		next := words[i+1]
+		if next == "тебе" || next == "тебя" || next == "за" {
+			return Result{CheckFeminine, false,
+				fmt.Sprintf("masculine self-reference %q before %q", w, next)}
+		}
+	}
+	return Result{CheckFeminine, true, ""}
+}
+
+// --- the cringe checks ---------------------------------------------------
+//
+// "Think Jarvis without the cringe part". DESIGN.md § Non-goals: "Not a
+// relationship — mom-tone is a function that makes nudges land, not emotional
+// company. Names the drift a warm small model falls into." Each pattern below
+// is one shape of that drift. They are deliberately specific: a check that
+// flags any warmth at all would make the nudges robotic, which is the other
+// failure.
+
+type cringePattern struct {
+	// what the pattern is defending against, shown in the failure detail.
+	why string
+	pat *regexp.Regexp
+}
+
+var cringePatterns = []cringePattern{
+	{
+		// Endearments. "Not a relationship" — a pet name reframes a nudge as
+		// intimacy, and the operator asked for mother-like, not girlfriend-like.
+		why: "pet name / endearment",
+		// No \b around the Russian alternatives: Go's RE2 \b is ASCII-only and
+		// never matches at a Cyrillic boundary, so anchoring them would make
+		// this check silently always pass.
+		pat: regexp.MustCompile(`(?i)(милый|дорогой|солнышко|солнце моё|солнце мое|зайчик|котик|сладкий|малыш|дружок|родной|любимый|\bhoney\b|\bsweetie\b|\bdarling\b|\bbuddy\b)`),
+	},
+	{
+		// Emoji. The nudge is spoken aloud; an emoji is either silence or a TTS
+		// artefact. Also the single loudest cringe signal in a small model.
+		why: "emoji",
+		pat: nil, // handled by hasEmoji, ranges don't fit a regexp cleanly
+	},
+	{
+		// Exclamation pileup. One "!" is emphasis; two is a cheerleader.
+		why: "more than one exclamation mark",
+		pat: regexp.MustCompile(`!.*!|!!`),
+	},
+	{
+		// Fake concern. She has no feelings to report, and reporting them makes
+		// the nudge about her instead of about the water.
+		why: "fake concern opener",
+		pat: regexp.MustCompile(`(?i)(я волну|я беспоко|беспокоюсь|переживаю|я забочусь|я тревож|мне тревожно|i'?m worried)`),
+	},
+	{
+		// Apologising. The rule decided she speaks. Apologising for a greenlit
+		// nudge undermines the one thing that makes nudges land.
+		why: "apology",
+		pat: regexp.MustCompile(`(?i)(извини|прости|сожалею|прошу прощения|не хочу мешать|не хочу отвлекать|sorry|apolog)`),
+	},
+	{
+		// Offering emotional support. The explicit "not emotional company" line.
+		why: "offer of emotional support",
+		pat: regexp.MustCompile(`(?i)(я рядом|я здесь для теб|ты не один|всё будет хорошо|все будет хорошо|не переживай|я с тобой|обнимаю|я поддерж|держись)`),
+	},
+	{
+		// Asking how he feels. Turns a one-way nudge into a conversation he now
+		// owes an answer to — the most reliable way to make him mute it.
+		why: "asking how he feels",
+		pat: regexp.MustCompile(`(?i)(как ты\s*[?.!]|как ты себя|как самочувств|как настроение|всё ли в порядке|все ли в порядке|ты в порядке|how are you)`),
+	},
+	{
+		// Praise for compliance. Rewards make the nudge a training exercise;
+		// "not a relationship" again, from the other side.
+		why: "praise / reward framing",
+		pat: regexp.MustCompile(`(?i)(молодец|умница|ты справ|гордюсь|горжусь|отличная работа|так держать|good job|proud of you)`),
+	},
+}
+
+// hasEmoji — the pictographic ranges plus the variation selector. Cyrillic and
+// ordinary punctuation are far below all of these.
+func hasEmoji(s string) bool {
+	for _, r := range s {
+		switch {
+		case r >= 0x1F000 && r <= 0x1FAFF,
+			r >= 0x2600 && r <= 0x27BF,
+			r >= 0x2B00 && r <= 0x2BFF,
+			r == 0xFE0F, r == 0x203C, r == 0x2049:
+			return true
+		}
+	}
+	return false
+}
+
+func checkCringe(body string) Result {
+	for _, c := range cringePatterns {
+		if c.pat == nil {
+			if hasEmoji(body) {
+				return Result{CheckCringe, false, c.why}
+			}
+			continue
+		}
+		if m := c.pat.FindString(body); m != "" {
+			return Result{CheckCringe, false, fmt.Sprintf("%s (%q)", c.why, m)}
+		}
+	}
+	return Result{CheckCringe, true, ""}
+}
+
+// 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 {
+	low := strings.ToLower(body)
+	for _, want := range c.WantAny {
+		if strings.Contains(low, strings.ToLower(want)) {
+			return Result{CheckOnTopic, true, ""}
+		}
+	}
+	return Result{CheckOnTopic, false,
+		fmt.Sprintf("mentions none of %v", c.WantAny)}
+}

internal/phraser/eval/eval.go

@@ -0,0 +1,334 @@
+// Package eval scores nudge phrasing — the sentences the operator actually
+// hears. It is the phrasing counterpart to internal/router/eval.
+//
+// Why a separate package from phraser: the fixture must be scorable by BOTH
+// phrasing paths (the deterministic Stub and the resident model) from outside
+// the phraser package, and a _test.go file inside phraser cannot be imported.
+// So the fixture is embedded here and the scorer takes a Nudger interface.
+//
+// Why deterministic checks and not model judgement: the resident model is a
+// 0.8B. It cannot grade its own tone. Every check in checks.go is a string or
+// length test that a human can read and disagree with. A score here is a claim
+// about measurable properties, not about whether a sentence is good.
+//
+// DESIGN.md § "Rules decide, LLM phrases" is why there is no send/veto signal
+// anywhere in this package: the rule already decided she speaks. The phraser
+// only words it, so a nudge the model refuses to write is a failure, never a
+// legitimate outcome.
+package eval
+
+import (
+	"context"
+	_ "embed"
+	"encoding/json"
+	"fmt"
+	"sort"
+	"strings"
+	"time"
+
+	"github.com/kami/maven/internal/delivery"
+	"github.com/kami/maven/internal/loop"
+	"github.com/kami/maven/internal/store"
+)
+
+//go:embed nudges_v1.json
+var fixtureJSON []byte
+
+// SchemaVersion — the version this package understands.
+const SchemaVersion = 1
+
+// Case — one nudge situation, as a real tick would present it. The fields are
+// the (rule, severity, context) input DESIGN.md names, flattened to JSON.
+//
+// WantAny is the on-topic contract: at least one of these lowercased fragments
+// must appear in the message. A water nudge that never mentions water is a
+// failure however charming it reads. Fragments are stems ("вод") so declension
+// does not defeat the check, and they list both languages because the Stub is
+// still English (see the writeup).
+type Case struct {
+	ID       string `json:"id"`
+	Rule     string `json:"rule"`
+	Severity int    `json:"severity"`
+
+	// SinceMinutes — age of the rule's own fact. 0 means "no such fact", which
+	// is the branch where the phraser has no duration to name.
+	SinceMinutes int `json:"since_minutes"`
+
+	// FactKey/FactValue/FactSource — the aggregate fact behind the ops rules.
+	// service_down phrasing reads the key for the service name.
+	FactKey    string `json:"fact_key,omitempty"`
+	FactValue  string `json:"fact_value,omitempty"`
+	FactSource string `json:"fact_source,omitempty"`
+
+	// QuietHours/CalendarBusy — the bad moments. The gate already let this
+	// nudge through (ops outranks quiet hours), so the phrasing still has to be
+	// short and plain rather than apologetic about the timing.
+	QuietHours   bool `json:"quiet_hours,omitempty"`
+	CalendarBusy bool `json:"calendar_busy,omitempty"`
+
+	WantAny []string `json:"want_any"`
+	Tags    []string `json:"tags,omitempty"`
+	Note    string   `json:"note,omitempty"`
+}
+
+// Fixture — the versioned envelope. SchemaVersion gates the loader so an older
+// binary refuses a fixture it would misread instead of reporting a wrong score.
+type Fixture struct {
+	SchemaVersion int      `json:"schema_version"`
+	Name          string   `json:"name"`
+	ReferenceNow  string   `json:"reference_now"`
+	Notes         []string `json:"notes"`
+	Cases         []Case   `json:"cases"`
+}
+
+// Load returns the embedded fixture.
+func Load() (Fixture, error) {
+	var f Fixture
+	if err := json.Unmarshal(fixtureJSON, &f); err != nil {
+		return Fixture{}, fmt.Errorf("parse fixture: %w", err)
+	}
+	if f.SchemaVersion != SchemaVersion {
+		return Fixture{}, fmt.Errorf("fixture schema_version %d, want %d", f.SchemaVersion, SchemaVersion)
+	}
+	if len(f.Cases) == 0 {
+		return Fixture{}, fmt.Errorf("fixture has no cases")
+	}
+	return f, nil
+}
+
+// Now — the fixture's reference clock, so fact ages are reproducible.
+func (f Fixture) Now() (time.Time, error) {
+	t, err := time.Parse(time.RFC3339, f.ReferenceNow)
+	if err != nil {
+		return time.Time{}, fmt.Errorf("parse reference_now %q: %w", f.ReferenceNow, err)
+	}
+	return t, nil
+}
+
+// Candidate rebuilds the loop.Candidate a tick would hand the phraser.
+func (c Case) Candidate(now time.Time) loop.Candidate {
+	state := loop.State{
+		Now:          now,
+		Facts:        map[string]store.Fact{},
+		QuietHours:   c.QuietHours,
+		CalendarBusy: c.CalendarBusy,
+	}
+	if c.SinceMinutes > 0 {
+		state.Facts[c.Rule] = store.Fact{
+			Key: c.Rule,
+			Ts:  now.Add(-time.Duration(c.SinceMinutes) * time.Minute),
+		}
+	}
+	if c.FactKey != "" {
+		state.Facts[c.Rule] = store.Fact{
+			Key:    c.FactKey,
+			Value:  c.FactValue,
+			Source: c.FactSource,
+			Ts:     now.Add(-time.Duration(c.SinceMinutes) * time.Minute),
+		}
+	}
+	sev := loop.Severity(c.Severity)
+	return loop.Candidate{
+		Rule:     loop.Rule{Name: c.Rule, Severity: sev},
+		Severity: sev,
+		State:    state,
+	}
+}
+
+// Nudger — the one thing a phrasing path must do to be scorable. Both
+// *phraser.Stub and *phraser.LLMPhraser satisfy it.
+type Nudger interface {
+	PhraseNudge(ctx context.Context, c loop.Candidate) (delivery.PhrasedNudge, error)
+}
+
+// Outcome — one scored case. Failed lists the check names that did not pass,
+// Reasons the human-readable detail. Failed is empty exactly when Pass is true.
+type Outcome struct {
+	Case    Case
+	Body    string
+	Mood    string
+	Err     error
+	Latency time.Duration
+	Pass    bool
+	Failed  []string
+	Reasons []string
+}
+
+// Report — the aggregate. ByCheck is the useful part: one composite percentage
+// hides which property broke, and tuning a prompt needs to know.
+type Report struct {
+	Name     string
+	Total    int
+	Passed   int
+	Errors   int
+	ByCheck  map[string]int
+	ByRule   map[string]TagStat
+	Outcomes []Outcome
+	P50      time.Duration
+	P95      time.Duration
+	Max      time.Duration
+}
+
+// TagStat — passed/total for one slice of the fixture.
+type TagStat struct{ Passed, Total int }
+
+// Accuracy — fraction of cases that passed every check.
+func (r Report) Accuracy() float64 {
+	if r.Total == 0 {
+		return 0
+	}
+	return float64(r.Passed) / float64(r.Total)
+}
+
+// Score runs every case through p and aggregates. A phrasing error scores as a
+// miss and is counted in Errors — "the model was down" and "the model wrote
+// something bad" are different numbers and a prompt change must not be able to
+// hide behind the first one.
+//
+// Latency is wall-clock per PhraseNudge call. On the CPU/iGPU target a nudge
+// the model takes a minute to word has already missed its moment.
+func Score(ctx context.Context, name string, p Nudger, f Fixture) (Report, error) {
+	now, err := f.Now()
+	if err != nil {
+		return Report{}, err
+	}
+	rep := Report{
+		Name:    name,
+		Total:   len(f.Cases),
+		ByCheck: map[string]int{},
+		ByRule:  map[string]TagStat{},
+	}
+	for _, name := range CheckNames {
+		rep.ByCheck[name] = 0
+	}
+	lat := make([]time.Duration, 0, len(f.Cases))
+
+	for _, c := range f.Cases {
+		start := time.Now()
+		pn, err := p.PhraseNudge(ctx, c.Candidate(now))
+		o := Outcome{Case: c, Body: pn.Body, Mood: pn.Mood, 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 RunChecks(c, pn.Body, pn.Mood) {
+				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.ByRule, ruleFamily(c.Rule), 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
+}
+
+// ruleFamily collapses "routine:зарядка" to "routine" so the per-rule table
+// stays readable however many routines the operator configures.
+func ruleFamily(rule string) string {
+	if i := strings.IndexByte(rule, ':'); i > 0 {
+		return rule[:i]
+	}
+	return rule
+}
+
+func bump(m map[string]TagStat, key string, pass bool) {
+	if key == "" {
+		return
+	}
+	s := m[key]
+	s.Total++
+	if pass {
+		s.Passed++
+	}
+	m[key] = s
+}
+
+// percentile — nearest-rank on a pre-sorted slice. No interpolation: with ~15
+// samples an interpolated p95 invents a latency no call actually took.
+func percentile(sorted []time.Duration, p float64) time.Duration {
+	if len(sorted) == 0 {
+		return 0
+	}
+	i := int(p * float64(len(sorted)))
+	if i >= len(sorted) {
+		i = len(sorted) - 1
+	}
+	return sorted[i]
+}
+
+// String renders the comparison table — composite score, then per-check so a
+// regression names the property it broke, then latency.
+func (r Report) 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 CheckNames {
+		fmt.Fprintf(&b, "  %-9s %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 rule: %s\n", renderStats(r.ByRule))
+	return b.String()
+}
+
+// Failures — per-case detail, sorted by ID so two runs diff cleanly.
+func (r Report) 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.Body, strings.Join(o.Reasons, "; "))
+	}
+	return b.String()
+}
+
+// Messages — every generated message verbatim, pass or fail. This is what a
+// human reads to judge tone; the score only says which checks fired.
+func (r Report) Messages() string {
+	var b strings.Builder
+	for _, o := range r.sorted() {
+		mark := "ok  "
+		if !o.Pass {
+			mark = "FAIL"
+		}
+		fmt.Fprintf(&b, "  %s %-22s [%s] %q\n", mark, o.Case.ID, o.Mood, o.Body)
+	}
+	return b.String()
+}
+
+func (r Report) sorted() []Outcome {
+	out := append([]Outcome(nil), r.Outcomes...)
+	sort.Slice(out, func(i, j int) bool { return out[i].Case.ID < out[j].Case.ID })
+	return out
+}
+
+func renderStats(m map[string]TagStat) string {
+	keys := make([]string, 0, len(m))
+	for k := range m {
+		keys = append(keys, k)
+	}
+	sort.Strings(keys)
+	parts := make([]string, 0, len(keys))
+	for _, k := range keys {
+		parts = append(parts, fmt.Sprintf("%s %d/%d", k, m[k].Passed, m[k].Total))
+	}
+	return strings.Join(parts, "  ")
+}

internal/phraser/eval/eval_test.go

@@ -0,0 +1,179 @@
+package eval
+
+import (
+	"context"
+	"strings"
+	"testing"
+
+	"github.com/kami/maven/internal/loop"
+	"github.com/kami/maven/internal/phraser"
+)
+
+func TestLoadFixture(t *testing.T) {
+	f, err := Load()
+	if err != nil {
+		t.Fatalf("Load: %v", err)
+	}
+	if _, err := f.Now(); err != nil {
+		t.Fatalf("Now: %v", err)
+	}
+	seen := map[string]bool{}
+	for _, c := range f.Cases {
+		if seen[c.ID] {
+			t.Errorf("duplicate case id %q", c.ID)
+		}
+		seen[c.ID] = true
+		if c.Rule == "" || c.Severity < 1 || c.Severity > 4 {
+			t.Errorf("%s: rule %q severity %d", c.ID, c.Rule, c.Severity)
+		}
+		if len(c.WantAny) == 0 {
+			t.Errorf("%s: no want_any, the on-topic check would always pass", c.ID)
+		}
+	}
+	// Coverage floor: all five loop rules plus both minted families, or the
+	// fixture measures a subset and the score does not mean what it says.
+	for _, rule := range []string{"water", "meal", "break", "service_down", "netdata_critical", "routine", "morning"} {
+		found := false
+		for _, c := range f.Cases {
+			if ruleFamily(c.Rule) == rule {
+				found = true
+			}
+		}
+		if !found {
+			t.Errorf("no case for rule family %q", rule)
+		}
+	}
+}
+
+// TestStubBaseline is the CI ratchet: the deterministic Stub, no model, no
+// network. The floor is low on purpose — the Stub is English template phrasing,
+// so it fails `lang` on every case by construction. The point of the ratchet is
+// that the checks keep running and the Stub does not get worse, not that the
+// Stub is good.
+func TestStubBaseline(t *testing.T) {
+	f, err := Load()
+	if err != nil {
+		t.Fatalf("Load: %v", err)
+	}
+	rep, err := Score(context.Background(), "stub (deterministic floor)", phraser.NewStub(), f)
+	if err != nil {
+		t.Fatalf("Score: %v", err)
+	}
+	t.Log("\n" + rep.String() + rep.Messages())
+
+	if rep.Errors != 0 {
+		t.Errorf("stub returned %d errors — the deterministic path must never fail", rep.Errors)
+	}
+	// Per-check ratchets rather than one composite: the Stub's composite is 0
+	// (it never passes `lang`), so a composite floor would catch nothing.
+	floors := map[string]int{
+		CheckMood: 15,
+		// 12, not 15: the Stub's `break` template genuinely runs past the
+		// ceiling ("you've been at your desk for 4 hours without a break — step
+		// away for a bit." is 76 chars but 16 words). Left failing rather than
+		// raising the ceiling to hide it.
+		CheckLength:   12,
+		CheckFeminine: 15,
+		CheckCringe:   15,
+		CheckOnTopic:  12,
+	}
+	for name, floor := range floors {
+		if rep.ByCheck[name] < floor {
+			t.Errorf("check %s: %d/%d, below ratchet %d — phrasing regressed",
+				name, rep.ByCheck[name], rep.Total, floor)
+		}
+	}
+}
+
+// TestChecksCatchWhatTheyClaim — the checks are the measurement, so they get
+// their own tests. Without these, a bad regexp would silently make every
+// phrasing run look clean.
+func TestChecksCatchWhatTheyClaim(t *testing.T) {
+	water := Case{Rule: "water", WantAny: []string{"вод"}}
+
+	cases := []struct {
+		name string
+		body string
+		want string // the check that must fail, "" for a clean message
+	}{
+		{"clean", "уже четыре часа без воды — попей.", ""},
+		{"long", "уже четыре часа без воды, а это довольно много, и вообще пить надо регулярно, иначе будет плохо совсем", CheckLength},
+		{"english", "you haven't had water in 4 hours, drink something", CheckLang},
+		{"masculine self", "я напомнил про воду.", CheckFeminine},
+		{"masculine dropped pronoun", "напомнил тебе про воду.", CheckFeminine},
+		{"masculine predicative", "я должен сказать: попей воды.", CheckFeminine},
+		// The other direction: HE is male, so second-person masculine is right.
+		{"second person masculine ok", "ты не пил воду четыре часа.", ""},
+		{"feminine self ok", "я заметила: воды не было четыре часа.", ""},
+		{"pet name", "милый, попей воды.", CheckCringe},
+		{"emoji", "попей воды 💧", CheckCringe},
+		{"exclamations", "попей воды!!", CheckCringe},
+		{"fake concern", "я беспокоюсь: воды не было четыре часа.", CheckCringe},
+		{"apology", "извини, что отвлекаю — попей воды.", CheckCringe},
+		{"emotional support", "я рядом, ты не один. попей воды.", CheckCringe},
+		{"asks how he feels", "как ты себя чувствуешь? попей воды.", CheckCringe},
+		{"praise", "молодец! теперь попей воды.", CheckCringe},
+		{"off topic", "пора бы уже что-то сделать.", CheckOnTopic},
+	}
+
+	for _, tc := range cases {
+		t.Run(tc.name, func(t *testing.T) {
+			var failed []string
+			for _, r := range RunChecks(water, tc.body, "neutral") {
+				if !r.Pass {
+					failed = append(failed, r.Name+"("+r.Detail+")")
+				}
+			}
+			joined := strings.Join(failed, " ")
+			switch {
+			case tc.want == "" && len(failed) > 0:
+				t.Errorf("clean message flagged: %s", joined)
+			case tc.want != "" && !strings.Contains(joined, tc.want+"("):
+				t.Errorf("want %s to fail, got %q", tc.want, joined)
+			}
+		})
+	}
+}
+
+func TestMoodCheckUsesTheEnum(t *testing.T) {
+	if r := checkMood("cheerful"); r.Pass {
+		t.Error("mood outside the enum passed")
+	}
+	if r := checkMood(""); r.Pass {
+		t.Error("empty mood passed")
+	}
+	for m := range Moods {
+		if r := checkMood(m); !r.Pass {
+			t.Errorf("enum mood %q failed", m)
+		}
+	}
+}
+
+// TestCandidateCarriesTheContext — the whole harness is worthless if the
+// Candidate it builds does not carry the duration the prompt is supposed to
+// name.
+func TestCandidateCarriesTheContext(t *testing.T) {
+	f, err := Load()
+	if err != nil {
+		t.Fatalf("Load: %v", err)
+	}
+	now, _ := f.Now()
+	for _, c := range f.Cases {
+		cand := c.Candidate(now)
+		if cand.Rule.Name != c.Rule || cand.Severity != loop.Severity(c.Severity) {
+			t.Errorf("%s: candidate lost rule or severity", c.ID)
+		}
+		if c.SinceMinutes > 0 {
+			d, ok := cand.State.Since(c.Rule)
+			if !ok || int(d.Minutes()) != c.SinceMinutes {
+				t.Errorf("%s: since %v ok=%v, want %d minutes", c.ID, d, ok, c.SinceMinutes)
+			}
+		}
+		if c.FactKey != "" {
+			fact, ok := cand.State.Fact(c.Rule)
+			if !ok || fact.Key != c.FactKey {
+				t.Errorf("%s: fact key %q, want %q", c.ID, fact.Key, c.FactKey)
+			}
+		}
+	}
+}

internal/phraser/eval/llmphraser_test.go

@@ -0,0 +1,73 @@
+package eval
+
+import (
+	"context"
+	"os"
+	"strings"
+	"testing"
+	"time"
+
+	"github.com/kami/maven/internal/phraser"
+)
+
+// TestLLMPhrasingBaseline — the resident model wording real nudges. Opt-in,
+// same shape as internal/router/eval's MAVEN_LLM_URL gate, because CI has no
+// model and a phrasing run costs minutes on the CPU target.
+//
+//	llama-server -m /mnt/hdd1/llms/qwen3.5/Qwen3.5-0.8B.Q4_K_M.gguf \
+//	  --host 127.0.0.1 --port 18099 -c 2048 -ngl 99
+//	MAVEN_LLM_URL=http://127.0.0.1:18099 make eval-phrasing
+//
+// It reports and does not assert a quality bar. The numbers are the input to
+// tuning the persona prompt; an assertion here would be the test inventing the
+// bar rather than measuring against it. The one thing worth failing on is a
+// harness fault — every case erroring means the run measured infrastructure.
+func TestLLMPhrasingBaseline(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)")
+	}
+	// A local llama-server must not go through an HTTP proxy. This box proxies
+	// loopback through a SOCKS bridge that answers 503, which would score every
+	// case as a phrasing error and read as "the model cannot phrase".
+	noProxyLoopback(t)
+
+	f, err := Load()
+	if err != nil {
+		t.Fatalf("Load: %v", err)
+	}
+
+	cfg := phraser.DefaultConfig("")
+	// Generous: an unconstrained 0.8B can spend a minute thinking before it
+	// writes a word, and a timeout would be scored as a model failure.
+	cfg.Timeout = 5 * time.Minute
+	p := phraser.NewLLMPhraserAt(base, cfg)
+	defer p.Close()
+
+	rep, err := Score(context.Background(), "llm (0.8B, built-in persona)", p, f)
+	if err != nil {
+		t.Fatalf("Score: %v", err)
+	}
+	t.Log("\n" + rep.String() + "\nmessages:\n" + rep.Messages() + "\nfailures:\n" + rep.Failures())
+
+	if rep.Errors == rep.Total {
+		t.Errorf("all %d cases errored — harness fault, not a measurement", rep.Total)
+	}
+}
+
+// noProxyLoopback appends the loopback host to no_proxy before any request, so
+// http.ProxyFromEnvironment (which caches the environment on first use) sees it.
+func noProxyLoopback(t *testing.T) {
+	t.Helper()
+	for _, key := range []string{"no_proxy", "NO_PROXY"} {
+		cur := os.Getenv(key)
+		if strings.Contains(cur, "127.0.0.1") {
+			continue
+		}
+		if cur == "" {
+			t.Setenv(key, "127.0.0.1,localhost")
+			continue
+		}
+		t.Setenv(key, cur+",127.0.0.1,localhost")
+	}
+}

internal/phraser/eval/nudges_v1.json

@@ -0,0 +1,158 @@
+{
+  "schema_version": 1,
+  "name": "nudge phrasing v1",
+  "reference_now": "2026-07-31T21:40:00+03:00",
+  "notes": [
+    "The five loop rules (water, meal, break, service_down, netdata_critical) plus one routine: and one morning: case, at the severities they actually ship with.",
+    "The bad-moment cases (quiet_hours, calendar_busy) are here because the gate already let them through — ops outranks quiet hours. The phrasing must stay short and plain, not apologise for the timing.",
+    "want_any lists stems, not whole words, so declension does not defeat the on-topic check. English stems are included because the deterministic Stub is still English.",
+    "There is no expected message. The checks measure properties, not similarity to a reference sentence — a fixed golden string would just freeze one arbitrary phrasing."
+  ],
+  "cases": [
+    {
+      "id": "water-3h",
+      "rule": "water",
+      "severity": 1,
+      "since_minutes": 190,
+      "want_any": ["вод", "попей", "пить", "выпей", "напит", "water", "drink"],
+      "tags": ["care"],
+      "note": "The base case. Just over the 3h predicate."
+    },
+    {
+      "id": "water-7h",
+      "rule": "water",
+      "severity": 1,
+      "since_minutes": 430,
+      "want_any": ["вод", "попей", "пить", "выпей", "напит", "water", "drink"],
+      "tags": ["care"],
+      "note": "Long overdue. Severity is unchanged, so the phrasing must not escalate into alarm."
+    },
+    {
+      "id": "water-busy",
+      "rule": "water",
+      "severity": 1,
+      "since_minutes": 240,
+      "calendar_busy": true,
+      "want_any": ["вод", "попей", "пить", "выпей", "напит", "water", "drink"],
+      "tags": ["care", "bad-moment"],
+      "note": "Mid-meeting. A bad moment invites an apology, which is the check that should catch it."
+    },
+    {
+      "id": "meal-7h",
+      "rule": "meal",
+      "severity": 1,
+      "since_minutes": 420,
+      "want_any": ["ешь", "еда", "еды", "поешь", "перекус", "обед", "ужин", "покуш", "food", "eat"],
+      "tags": ["care"]
+    },
+    {
+      "id": "meal-11h-quiet",
+      "rule": "meal",
+      "severity": 1,
+      "since_minutes": 660,
+      "quiet_hours": true,
+      "want_any": ["ешь", "еда", "еды", "поешь", "перекус", "обед", "ужин", "покуш", "food", "eat"],
+      "tags": ["care", "bad-moment"],
+      "note": "Quiet hours suppresses care nudges in the gate, so this one only reaches the phraser via an explicit override. Included because it is the shape most likely to draw a hedge."
+    },
+    {
+      "id": "break-90m",
+      "rule": "break",
+      "severity": 2,
+      "since_minutes": 95,
+      "want_any": ["перерыв", "разомн", "встань", "отдохн", "пауз", "отойд", "размин", "break", "step away"],
+      "tags": ["care"]
+    },
+    {
+      "id": "break-4h",
+      "rule": "break",
+      "severity": 2,
+      "since_minutes": 240,
+      "want_any": ["перерыв", "разомн", "встань", "отдохн", "пауз", "отойд", "размин", "break", "step away"],
+      "tags": ["care"]
+    },
+    {
+      "id": "break-busy",
+      "rule": "break",
+      "severity": 2,
+      "since_minutes": 150,
+      "calendar_busy": true,
+      "want_any": ["перерыв", "разомн", "встань", "отдохн", "пауз", "отойд", "размин", "break", "step away"],
+      "tags": ["care", "bad-moment"]
+    },
+    {
+      "id": "service-down",
+      "rule": "service_down",
+      "severity": 4,
+      "since_minutes": 3,
+      "fact_key": "vaultwarden",
+      "fact_value": "\"down\"",
+      "fact_source": "poll:uptimekuma",
+      "want_any": ["vaultwarden", "сервис", "упал", "не отвеч", "лежит", "недоступ", "down", "service"],
+      "tags": ["ops"],
+      "note": "The service name is in the fact key, not the value. A nudge that says 'a service' without naming it is on-topic but useless — the on-topic check cannot catch that, a human reading Messages() can."
+    },
+    {
+      "id": "service-down-night",
+      "rule": "service_down",
+      "severity": 4,
+      "since_minutes": 2,
+      "quiet_hours": true,
+      "fact_key": "nextcloud",
+      "fact_value": "\"down\"",
+      "fact_source": "poll:uptimekuma",
+      "want_any": ["nextcloud", "сервис", "упал", "не отвеч", "лежит", "недоступ", "down", "service"],
+      "tags": ["ops", "bad-moment"],
+      "note": "03:00-shaped. Sev4 outranks quiet hours by design, so she speaks — plainly, without softening it into a maybe."
+    },
+    {
+      "id": "netdata-disk",
+      "rule": "netdata_critical",
+      "severity": 3,
+      "since_minutes": 5,
+      "fact_key": "netdata_alarm",
+      "fact_value": "\"critical\"",
+      "fact_source": "poll:netdata",
+      "want_any": ["netdata", "диск", "критич", "алярм", "аларм", "тревог", "место", "памят", "critical", "alarm", "disk"],
+      "tags": ["ops"]
+    },
+    {
+      "id": "netdata-busy",
+      "rule": "netdata_critical",
+      "severity": 3,
+      "since_minutes": 12,
+      "calendar_busy": true,
+      "fact_key": "netdata_alarm",
+      "fact_value": "\"critical\"",
+      "fact_source": "poll:netdata",
+      "want_any": ["netdata", "диск", "критич", "алярм", "аларм", "тревог", "место", "памят", "critical", "alarm", "disk"],
+      "tags": ["ops", "bad-moment"]
+    },
+    {
+      "id": "routine-pills",
+      "rule": "routine:таблетки",
+      "severity": 2,
+      "since_minutes": 0,
+      "want_any": ["таблетк", "приня", "лекарств", "pill"],
+      "tags": ["routine"],
+      "note": "A routine: rule has no fact of its own, so there is no duration to name. The rule name is the only context."
+    },
+    {
+      "id": "routine-stretch",
+      "rule": "routine:зарядка",
+      "severity": 1,
+      "since_minutes": 0,
+      "want_any": ["зарядк", "размин", "упражн", "потянис", "разомн", "stretch", "exercise"],
+      "tags": ["routine"]
+    },
+    {
+      "id": "morning-checklist",
+      "rule": "morning:утро",
+      "severity": 2,
+      "since_minutes": 0,
+      "want_any": ["утр", "чеклист", "список", "не сделан", "осталось", "morning"],
+      "tags": ["routine"],
+      "note": "In production cmd/mavend/tick.go phrases morning routines deterministically and never calls the LLM. Scored anyway: the phraser is reachable with this rule name, and a fallback that garbles it is still a bug."
+    }
+  ]
+}

internal/phraser/llmphraser.go

@@ -67,6 +67,22 @@ func NewLLMPhraser(ctx context.Context, cfg Config) (*LLMPhraser, error) {
 	return p, nil
 }
 
+// NewLLMPhraserAt wires a phraser to a llama-server that someone else started
+// and owns. It spawns nothing, so Close does not kill anything.
+//
+// This exists for the phrasing scorer (internal/phraser/eval), which must
+// measure the phrasing against a shared llama-server without taking the model
+// load hit per run or killing a server another process depends on. The daemon
+// still uses NewLLMPhraser and still owns its own child process.
+func NewLLMPhraserAt(baseURL string, cfg Config) *LLMPhraser {
+	return &LLMPhraser{
+		cfg:    cfg,
+		client: &http.Client{Timeout: cfg.Timeout},
+		port:   strings.TrimSuffix(baseURL, "/"),
+		cancel: func() {},
+	}
+}
+
 func (p *LLMPhraser) start(ctx context.Context) error {
 	args := []string{
 		"-m", p.cfg.ModelPath,

internal/phraser/phraser.go

@@ -92,7 +92,11 @@ func (s *Stub) Close() error { return nil }
 // the predicate fire (the same State the predicate saw).
 func (s *Stub) PhraseNudge(_ context.Context, c loop.Candidate) (delivery.PhrasedNudge, error) {
 	body, summary := phraseNudge(c)
-	return delivery.PhrasedNudge{Candidate: c, Body: body, Summary: summary}, nil
+	// "neutral" rather than empty: Mood is part of the documented output
+	// contract and the Stub is a production fallback, so it must satisfy the
+	// contract too. Template phrasing has no tone to report, and neutral is the
+	// enum's own default.
+	return delivery.PhrasedNudge{Candidate: c, Body: body, Summary: summary, Mood: "neutral"}, nil
 }
 
 // PhraseReminder — extracts the user's text from the reminder payload (raw

internal/router/eval/llmrouter_test.go

@@ -23,7 +23,11 @@ import (
 //
 //	llama-server -m /mnt/hdd1/llms/qwen3.5/Qwen3.5-0.8B.Q4_K_M.gguf \
 //	  --host 127.0.0.1 --port 18099 -c 2048 -ngl 99
-//	MAVEN_LLM_URL=http://127.0.0.1:18099 make eval-router
+//	MAVEN_LLM_URL=http://127.0.0.1:18099 make eval-models
+//
+// Every report name carries the model llama-server reports over /v1/models, so
+// a bake-off across checkpoints (#278, #250) produces tables you can tell
+// apart. Point the variable at one server at a time.
 //
 // Three configurations, because "the LLM router" is ambiguous and the three
 // numbers answer different questions:
@@ -53,6 +57,14 @@ func TestLLMRouterBaseline(t *testing.T) {
 	}
 
 	ctx := context.Background()
+	model, err := ModelID(ctx, base)
+	if err != nil {
+		// Not fatal: an unlabelled score is still a score. But say so loudly,
+		// because an unlabelled row in a bake-off table is worthless.
+		t.Logf("could not read model id from %s: %v — reports will say %q", base, err, "unknown-model")
+		model = "unknown-model"
+	}
+	t.Logf("scoring model %s at %s", model, base)
 	lr := router.NewLLMRouter(client)
 
 	// llm-only: the LLM stage in isolation. Route returns (Decision, ok, err);
@@ -68,7 +80,7 @@ func TestLLMRouterBaseline(t *testing.T) {
 		}
 		return d, nil
 	})
-	repLLM, err := Score(ctx, "llm-only (0.8B, as deployed)", llmOnly, f)
+	repLLM, err := Score(ctx, "llm-only ("+model+", as deployed)", llmOnly, f)
 	if err != nil {
 		t.Fatalf("Score llm-only: %v", err)
 	}
@@ -77,7 +89,7 @@ func TestLLMRouterBaseline(t *testing.T) {
 	// cascade+llm: stage-0 grammar → LLM → classifier fallback, the wiring #320
 	// proposes. Hash embedder for the fallback so the classifier contribution is
 	// the deterministic floor and any lift is attributable to the model.
-	repCascade, err := Score(ctx, "cascade+llm (0.8B) + hash fallback",
+	repCascade, err := Score(ctx, "cascade+llm ("+model+") + hash fallback",
 		newBaselineRouter(t, router.NewHashEmbedder(1024), lr), f)
 	if err != nil {
 		t.Fatalf("Score cascade: %v", err)
@@ -96,7 +108,7 @@ func TestLLMRouterBaseline(t *testing.T) {
 	// either way. Kept so the question stays answered instead of being
 	// re-asked, and so internal/llm does NOT grow a chat_template_kwargs field
 	// for a problem that does not exist.
-	repNoThink, err := Score(ctx, "llm-only (0.8B, thinking off) [diagnostic]",
+	repNoThink, err := Score(ctx, "llm-only ("+model+", thinking off) [diagnostic]",
 		RouterFunc(func(ctx context.Context, u string, now time.Time) (router.Decision, error) {
 			d, ok, err := router.NewLLMRouter(&noThinkCompleter{base: base, http: &http.Client{Timeout: 60 * time.Second}}).Route(ctx, u, now)
 			if err != nil {

internal/router/eval/modelid.go

@@ -0,0 +1,51 @@
+package eval
+
+import (
+	"context"
+	"encoding/json"
+	"fmt"
+	"net/http"
+	"strings"
+)
+
+// ModelID asks llama-server which model it has loaded, so a scoring run can
+// label itself. Without this a bake-off between two models produces two tables
+// that look identical, and the operator has to remember which server was up.
+//
+// Read from the server rather than passed in on purpose: a hand-typed label
+// goes stale the moment someone restarts the server with a different -m.
+func ModelID(ctx context.Context, base string) (string, error) {
+	req, err := http.NewRequestWithContext(ctx, "GET", strings.TrimSuffix(base, "/")+"/v1/models", nil)
+	if err != nil {
+		return "", err
+	}
+	resp, err := http.DefaultClient.Do(req)
+	if err != nil {
+		return "", err
+	}
+	defer resp.Body.Close()
+	if resp.StatusCode != 200 {
+		return "", fmt.Errorf("models: status %d", resp.StatusCode)
+	}
+	var out struct {
+		Data []struct {
+			ID string `json:"id"`
+		} `json:"data"`
+	}
+	if err := json.NewDecoder(resp.Body).Decode(&out); err != nil {
+		return "", err
+	}
+	if len(out.Data) == 0 {
+		return "", fmt.Errorf("models: empty list")
+	}
+	return shortModelID(out.Data[0].ID), nil
+}
+
+// shortModelID trims the path and the .gguf suffix — llama-server reports the
+// file name it was started with, which is too long for a table header.
+func shortModelID(id string) string {
+	if i := strings.LastIndexAny(id, "/\\"); i >= 0 {
+		id = id[i+1:]
+	}
+	return strings.TrimSuffix(id, ".gguf")
+}