feat(watchdog): Sentry flags + quarantine on above-band Jev verdicts (#44)

jev.go

@@ -313,6 +313,86 @@ func (f *Flock) ClassifyDivergence(ctx context.Context, state any, budgets ...*B
 	return p, ok
 }
 
+// watchdogQuestions is the Sentry's off-task check (E3, JEV_STRATEGIES
+// strategies 4 and 8): three crisp yes/no noul questions about one crow
+// message against the request it answers. noul carries no confidence, so the
+// probability itself is band-thresholded (strategy 3).
+var watchdogQuestions = map[string]any{
+	"answers_request": map[string]any{
+		"type":         "noul",
+		"instructions": "Does `message` actually deliver what `request` asked of `crow`?",
+		"criteria": map[string]string{
+			"true":  "It answers the request, or plainly takes it on.",
+			"false": "It talks around it, answers a different question, or is off-task.",
+		},
+	},
+	"states_fact_without_source": map[string]any{
+		"type":         "noul",
+		"instructions": "Does `message` assert a checkable fact while showing no source for it?",
+		"criteria": map[string]string{
+			"true":  "It states a specific, checkable fact (a number, a quote, an event) with no stated source.",
+			"false": "It is an opinion, a plan, or the facts it states are sourced.",
+		},
+	},
+	"contradicts_earlier": map[string]any{
+		"type":         "noul",
+		"instructions": "Does `message` contradict what the `earlier` delivers on the same request say?",
+		"criteria": map[string]string{
+			"true":  "It disagrees with an earlier deliver on the same request.",
+			"false": "It agrees with, or simply adds to, what `earlier` said.",
+		},
+	},
+}
+
+// ClassifyWatch asks the watchdog questions of one crow message and returns
+// each answer's noul probability. ok is false on transport error or a missing
+// answer (a noul answer always carries a probability).
+func (j *JevClient) ClassifyWatch(ctx context.Context, state any) (map[string]float64, bool) {
+	if j == nil {
+		return nil, false
+	}
+	answers, _, _, err := j.SystemOne(ctx, state, watchdogQuestions)
+	if err != nil {
+		return nil, false
+	}
+	scores := make(map[string]float64, len(watchdogQuestions))
+	for name := range watchdogQuestions {
+		a := answers[name]
+		if a.Noul == nil {
+			return nil, false
+		}
+		scores[name] = *a.Noul
+	}
+	return scores, true
+}
+
+// ClassifyWatch runs the watchdog check under the flock guardrails (cap,
+// timeout, flight log with the three noul probabilities recorded for
+// calibration, strategy 5).
+func (f *Flock) ClassifyWatch(ctx context.Context, state any, budgets ...*Budget) (map[string]float64, bool) {
+	if f.jev == nil {
+		return nil, false
+	}
+	for _, b := range budgets {
+		if err := b.Check(); err != nil {
+			return nil, false
+		}
+	}
+	release, slot := f.reserve(ctx)
+	if !slot {
+		return nil, false
+	}
+	defer release()
+	cctx, cancel := context.WithTimeout(ctx, f.g.CrowTimeout)
+	defer cancel()
+	start := time.Now()
+	scores, ok := f.jev.ClassifyWatch(cctx, state)
+	if f.log != nil {
+		f.log.Write(Event{Kind: "watch", Crow: "Sentry", Model: f.jev.model, Ms: time.Since(start).Milliseconds(), Prob: scores})
+	}
+	return scores, ok
+}
+
 // ClassifyKind tags a nest message under the same guardrails as any call:
 // flock cap, timeout and flight log, with the probabilities recorded.
 func (f *Flock) ClassifyKind(ctx context.Context, text string, budgets ...*Budget) (string, map[string]float64, bool) {