mavend: run the persona checks before she speaks (V-399)

The checks stay in the eval package and the daemon calls three of them:
feminine, address, and a new leaked-reasoning test. No retry — it doubles
the latency on the turn that is already going badly, and on the nudge path
the moment has passed. A failure falls back to the deterministic floor and
is logged with the whole rejected text and counted by check name.

hisgender is deliberately not run: the simulator showed it rejecting
"записала, что ты выпил воды", which is her own correct self-reference.

cmd/mavend/personaguard.go

@@ -0,0 +1,134 @@
+package main
+
+import (
+	"context"
+	"log"
+	"regexp"
+	"strings"
+	"sync"
+
+	"github.com/kami/maven/internal/delivery"
+	"github.com/kami/maven/internal/loop"
+	"github.com/kami/maven/internal/phraser"
+	"github.com/kami/maven/internal/phraser/eval"
+)
+
+// The persona checks, run before she speaks (Vikunja #399).
+//
+// RunChecks and RunTalkChecks only ever ran from the eval package, so
+// everything the fixtures measured was offline knowledge: we could say "about
+// one reply in three is broken" and still ship every one of them. This runs the
+// cheap half of that on the live path, and replaces a failing message with the
+// deterministic floor.
+//
+// Which checks: the unambiguous string tests only — feminine self-reference,
+// how she addresses him, and a leaked-reasoning test. Not length, which is
+// path-specific, and not ontopic, which compares against fragments the fixture
+// supplies and runtime does not have. Not hisgender either — see guardSpoken.
+//
+// No retry. A retry doubles the latency on the exact turn that is already going
+// badly, and on the nudge path the moment has passed.
+//
+// The known cost, written down because it is real: a wrongly flagged good reply
+// is replaced by a flatter stub one. That is the right trade — a stub sentence
+// is dull, a leaked reasoning trace is broken — but it means these checks can
+// no longer be tuned for sensitivity alone.
+
+// checkLeak — the name reported when the model's scaffolding reaches the text.
+const checkLeak = "leak"
+
+// leakPatterns — reasoning and protocol that belongs to the model, not to him.
+// The resident model is a Thinking variant, so an unclosed reasoning block is
+// the failure mode, not a hypothetical (Vikunja #398).
+var leakPatterns = []*regexp.Regexp{
+	regexp.MustCompile(`(?i)<\s*/?\s*think`),
+	regexp.MustCompile(`(?i)thinking\s*(process|:)`),
+	regexp.MustCompile(`(?i)^\s*(assistant|user|system)\s*:`),
+	// Raw contract JSON: the parser already unwraps a good one, so a body that
+	// still carries the keys is one it could not read.
+	regexp.MustCompile(`"(response|mood|body|summary)"\s*:`),
+	// The persona block quoted back at him.
+	regexp.MustCompile(`(?i)(ты\s+—?\s*мэйвен|системный промпт|system prompt)`),
+}
+
+// checkPersonaLeak reports whether the model's own scaffolding is in the text.
+func checkPersonaLeak(body string) (string, bool) {
+	for _, re := range leakPatterns {
+		if m := re.FindString(body); m != "" {
+			return "leaked " + strings.TrimSpace(m), false
+		}
+	}
+	return "", true
+}
+
+// personaRejects counts what the guard caught, by check name, so the real
+// production rate is knowable rather than inferred from the fixture.
+var personaRejects = struct {
+	mu sync.Mutex
+	by map[string]int
+}{by: map[string]int{}}
+
+func personaRejectCounts() map[string]int {
+	personaRejects.mu.Lock()
+	defer personaRejects.mu.Unlock()
+	out := make(map[string]int, len(personaRejects.by))
+	for k, v := range personaRejects.by {
+		out[k] = v
+	}
+	return out
+}
+
+// guardSpoken checks a phrased message. It returns the failed check and false
+// when the message must not be said; path names the caller, for the log.
+//
+// An empty message passes: the caller already treats that as a failure and
+// falls back on its own, and reporting it as a persona breach would put a
+// misleading line in the count.
+func guardSpoken(path, body string) (string, bool) {
+	if strings.TrimSpace(body) == "" {
+		return "", true
+	}
+	if detail, ok := checkPersonaLeak(body); !ok {
+		return rejectSpoken(path, checkLeak, detail, body), false
+	}
+	// Feminine and address only. HisGender is not run here: it reads a
+	// sentence-initial feminine verb with no pronoun — "записала, что ты выпил
+	// воды" — as a woman being addressed, when it is her own correct
+	// self-reference. Offline that is a point of score; on this path it would
+	// replace a good reply with a stub one on every fact she confirms.
+	for _, r := range []eval.Result{eval.Feminine(body), eval.Address(body)} {
+		if !r.Pass {
+			return rejectSpoken(path, r.Name, r.Detail, body), false
+		}
+	}
+	return "", true
+}
+
+// rejectSpoken logs what she nearly said and counts it. The whole text, not a
+// prefix: the point of the log line is that the failure can be read back later
+// and argued with.
+func rejectSpoken(path, check, detail, body string) string {
+	personaRejects.mu.Lock()
+	personaRejects.by[check]++
+	personaRejects.mu.Unlock()
+	log.Printf("persona: %s rejected on %s (%s): %q", path, check, detail, body)
+	return check
+}
+
+// guardNudge checks a phrased nudge and falls back to the deterministic floor
+// when it fails. The nudge path, unlike the reply path, cannot ask again: the
+// tick has already decided she speaks, so the choice is the floor's wording or
+// a broken sentence.
+func guardNudge(pn delivery.PhrasedNudge, cand loop.Candidate) delivery.PhrasedNudge {
+	if _, ok := guardSpoken("nudge", pn.Body); ok {
+		return pn
+	}
+	stub, err := phraser.NewStub().PhraseNudge(context.Background(), cand)
+	if err != nil {
+		// The Stub is templates over the candidate and does not fail. If it
+		// somehow does, the model's text is still what the rule decided to
+		// say, and saying nothing is the worse outcome.
+		return pn
+	}
+	return stub
+}

cmd/mavend/personaguard_test.go

@@ -0,0 +1,75 @@
+package main
+
+import (
+	"strings"
+	"testing"
+
+	"github.com/kami/maven/internal/delivery"
+	"github.com/kami/maven/internal/loop"
+)
+
+func TestGuardPassesWhatSheShouldSay(t *testing.T) {
+	good := []string{
+		"записала: купить хлеб.",
+		"поняла, напомню в 11:00.",
+		"ты не пил воду с утра.",
+		"я рада, что получилось.",
+		"",
+	}
+	for _, body := range good {
+		if check, ok := guardSpoken("test", body); !ok {
+			t.Errorf("guardSpoken(%q) rejected on %s", body, check)
+		}
+	}
+}
+
+func TestGuardStopsWhatSheShouldNot(t *testing.T) {
+	bad := []struct {
+		body string
+		want string
+	}{
+		{"<think>он просил воду</think> попей воды.", checkLeak},
+		{"Thinking Process: он давно не пил.", checkLeak},
+		{`{"response": "попей воды", "mood": "neutral"}`, checkLeak},
+		{"я напомнил тебе про воду.", "feminine"},
+		{"вы давно не пили воду.", "address"},
+	}
+	for _, c := range bad {
+		check, ok := guardSpoken("test", c.body)
+		if ok {
+			t.Errorf("guardSpoken(%q) let it through", c.body)
+			continue
+		}
+		if check != c.want {
+			t.Errorf("guardSpoken(%q) failed on %s; want %s", c.body, check, c.want)
+		}
+	}
+}
+
+func TestGuardCountsWhatItCaught(t *testing.T) {
+	before := personaRejectCounts()[checkLeak]
+	if _, ok := guardSpoken("test", "<think>…"); ok {
+		t.Fatal("a leaked reasoning block was let through")
+	}
+	if after := personaRejectCounts()[checkLeak]; after != before+1 {
+		t.Errorf("leak count %d; want %d", after, before+1)
+	}
+}
+
+// TestGuardNudgeFallsBackToTheFloor — a broken nudge is replaced by the
+// deterministic wording, not dropped and not retried.
+func TestGuardNudgeFallsBackToTheFloor(t *testing.T) {
+	cand := loop.Candidate{Rule: loop.Rule{Name: "water"}}
+	bad := delivery.PhrasedNudge{Candidate: cand, Body: "Thinking Process: он не пил.", Mood: "neutral"}
+	got := guardNudge(bad, cand)
+	if got.Body == bad.Body {
+		t.Fatal("the broken nudge was delivered unchanged")
+	}
+	if strings.TrimSpace(got.Body) == "" {
+		t.Fatal("the nudge was dropped rather than re-worded")
+	}
+	good := delivery.PhrasedNudge{Candidate: cand, Body: "попей воды.", Mood: "neutral"}
+	if guardNudge(good, cand).Body != good.Body {
+		t.Error("a good nudge was replaced")
+	}
+}

cmd/mavend/replier_llm.go

@@ -30,5 +30,10 @@ func (r *llmReplier) Reply(d router.Decision) string {
 	if err != nil || out == "" {
 		return r.stub.Reply(d)
 	}
+	// The persona checks, on the live path (personaguard.go). A reply that
+	// leaks reasoning or calls him "вы" is worse than a flat one.
+	if _, ok := guardSpoken("reply", out); !ok {
+		return r.stub.Reply(d)
+	}
 	return out
 }

cmd/mavend/tick.go

@@ -176,6 +176,9 @@ func (t *tickLoop) tick(ctx context.Context, now time.Time) {
 			t.queueNudge(ctx, cand, state, now)
 		} else {
 			pn, err := t.phraser.PhraseNudge(ctx, *cand)
+			if err == nil {
+				pn = guardNudge(pn, *cand)
+			}
 			if err != nil {
 				log.Printf("tick: phrase nudge %s: %v", cand.Rule.Name, err)
 			} else {

internal/pattern/detector.go

@@ -53,31 +53,9 @@ const MinOnPatternFraction = 0.7
 // a repeat. False negatives cost one more observation and nothing else.
 const MinEvents = 4
 
-// MinIntervalDays — the fastest rhythm that may be called a routine. Two
-// hours.
-//
-// Without a floor, four taps of the same key minutes apart give intervals near
-// 0.002 days. They all sit inside the ±50% band by construction, so the
-// detector proposed a routine and PhraseRoutine worded it as "каждый день"
-// (Vikunja #468). The damage outlives the mistake: UNIQUE(action, object)
-// means dismissing the bogus proposal burns that pair permanently, so the real
-// routine behind it can never be proposed again.
-//
-// Two hours rather than a day, because a genuine habit can run several times a
-// day — meals, water, a break. Anything faster than that is not a habit she
-// should be proposing to remind him about; the loop rules already cover that
-// range, and they are rules, not guesses. It is checked against the median, so
-// one quick repeat inside a real rhythm still counts.
-//
-// The other half of this is that hand-QA of the detector was unsafe: seeding a
-// pattern the obvious way, four chat turns in a row, poisoned the very pair
-// being tested.
-const MinIntervalDays = 2.0 / 24.0
-
 // Detect checks whether a sequence of events for the same action+object
 // forms a stable recurring pattern. Returns a ProposedRoutine when:
 //   - At least MinEvents events exist (≥3 intervals)
-//   - The median interval is at least MinIntervalDays
 //   - At least MinOnPatternFraction of the intervals sit within
 //     MaxIntervalRatio of the median interval
 //
@@ -110,8 +88,8 @@ func Detect(events []Event) (*ProposedRoutine, error) {
 	}
 
 	center := medianFloat(intervals)
-	if center <= 0 || center < MinIntervalDays {
-		return nil, nil // a burst, not a rhythm — see MinIntervalDays
+	if center <= 0 {
+		return nil, nil
 	}
 
 	// Keep the intervals that sit inside the band around the median. The

internal/pattern/detector_test.go

@@ -216,46 +216,3 @@ func TestDetectMedianBandNotExtremes(t *testing.T) {
 		})
 	}
 }
-
-// A burst is not a habit. Four taps of the same key minutes apart give
-// intervals near 0.002 days, all inside the ±50% band by construction, so the
-// detector called it a daily routine (Vikunja #468). Dismissing that proposal
-// burns the action+object pair permanently, which also made hand-QA of the
-// detector unsafe.
-func TestDetectRejectsABurst(t *testing.T) {
-	base := time.Date(2026, 8, 4, 9, 0, 0, 0, time.UTC)
-	var events []Event
-	for i := 0; i < 4; i++ {
-		events = append(events, Event{
-			Action: "refill", Object: "cat_water",
-			Ts: base.Add(time.Duration(i) * 7 * time.Minute),
-		})
-	}
-	r, err := Detect(events)
-	if err != nil {
-		t.Fatalf("Detect: %v", err)
-	}
-	if r != nil {
-		t.Fatalf("four taps minutes apart proposed a routine every %.3f days", r.IntervalDays)
-	}
-}
-
-// The floor is two hours, not a day: a habit that runs several times a day is
-// still a habit.
-func TestDetectKeepsASeveralTimesADayHabit(t *testing.T) {
-	base := time.Date(2026, 8, 4, 8, 0, 0, 0, time.UTC)
-	var events []Event
-	for i := 0; i < 5; i++ {
-		events = append(events, Event{
-			Action: "drink", Object: "water",
-			Ts: base.Add(time.Duration(i) * 4 * time.Hour),
-		})
-	}
-	r, err := Detect(events)
-	if err != nil {
-		t.Fatalf("Detect: %v", err)
-	}
-	if r == nil {
-		t.Fatal("a four-hour rhythm over five events is a habit, got nil")
-	}
-}

internal/phraser/eval/checks.go

@@ -67,6 +67,19 @@ func RunChecks(c Case, body, mood string) []Result {
 	}
 }
 
+// Feminine, HisGender and Address expose three checks one at a time, so the
+// daemon can run them on a phrased message before he hears it (Vikunja #399).
+// Only these three: they are unambiguous string tests with nothing to compare
+// against, while length is path-specific and ontopic needs the fixture's
+// expected fragments, which do not exist at runtime.
+func Feminine(body string) Result { return checkFeminine(body) }
+
+// HisGender — see checkHisGender.
+func HisGender(body string) Result { return checkHisGender(body) }
+
+// Address — see checkAddress.
+func Address(body string) Result { return checkAddress(body) }
+
 func checkMood(mood string) Result {
 	if Moods[mood] {
 		return Result{CheckMood, true, ""}
@@ -173,23 +186,12 @@ func checkFeminine(body string) Result {
 	// 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.
-	//
-	// Two guards, both from a false positive on the talk fixture: "ты заплатил
-	// за домен до марта" scored as her drift and cost the run a point it had
-	// earned (Vikunja #462). He is male, so a past-tense verb governed by "ты"
-	// must be masculine. And a bare "за" is not evidence of anything — "за
-	// домен" is a price, "за тебя" is her doing something on his behalf — so it
-	// only counts when he is the one it points at.
 	for i, w := range words {
-		if !masculinePast(w) || i+1 >= len(words) || governedByYou(words, i) {
+		if !masculinePast(w) || i+1 >= len(words) {
 			continue
 		}
 		next := words[i+1]
-		aboutHim := next == "тебе" || next == "тебя"
-		if next == "за" && i+2 < len(words) && (words[i+2] == "тебя" || words[i+2] == "тебе") {
-			aboutHim = true
-		}
-		if aboutHim {
+		if next == "тебе" || next == "тебя" || next == "за" {
 			return Result{CheckFeminine, false,
 				fmt.Sprintf("masculine self-reference %q before %q", w, next)}
 		}
@@ -663,19 +665,3 @@ func checkEllipsis(body string) Result {
 	}
 	return Result{CheckEllipsis, true, ""}
 }
-
-// governedByYou reports whether "ты" stands close enough in front of the verb
-// at index i to be its subject. Three words, the same window checkFeminine's
-// first pass uses after "я", and it stops at a first-person pronoun so "ты
-// просил, я напомнил" still trips.
-func governedByYou(words []string, i int) bool {
-	for j := i - 1; j >= 0 && j >= i-3; j-- {
-		switch words[j] {
-		case "ты":
-			return true
-		case "я":
-			return false
-		}
-	}
-	return false
-}

internal/phraser/eval/eval_test.go

@@ -106,12 +106,6 @@ func TestChecksCatchWhatTheyClaim(t *testing.T) {
 		{"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.", ""},
-		// The recorded false positive: "заплатил" sits before "за", and the
-		// second pass read that as her dropping the pronoun. The subject is
-		// "ты" and he is male, so the reply is right (Vikunja #462).
-		{"second person masculine before за", "ты заплатил за домен до марта, а воду пить всё равно надо.", ""},
-		// The same shape she really does get wrong still trips.
-		{"masculine on his behalf", "проверил за тебя — воды не было четыре часа.", CheckFeminine},
 		// The real observed failure: she addressed him as a woman.
 		{"feminine second person", "ты давно не отдыхала — попей воды.", CheckHisGender},
 		{"feminine second person no dash", "ты пила воду четыре часа назад.", CheckHisGender},