Wire voice-tapped facts into entity resolution; fix phraser model config

WriteFactReq gains an optional Subject field (empty = old behavior,
no CoreAPI signature change) and the IntentFact handler now passes the
fact's key as its resolution subject, so voice-tapped facts flow into
the Vikunja #279 enrichment queue automatically.

Also: deploy/mavend.json's phraser was pointed at a 4B model with
n_gpu_layers=99, which OOM'd under memory pressure and left a zombie
llama-server child. Swapped to the 2B Qwen model matching the intended
resident-model size, keeping GPU offload.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_018ghELqYhZNLub2TXGMazqA

cmd/mavend/fact_subject_test.go

@@ -0,0 +1,55 @@
+package main
+
+import (
+	"context"
+	"testing"
+	"time"
+
+	"github.com/kami/maven/internal/ipc"
+	"github.com/kami/maven/internal/memory"
+	"github.com/kami/maven/internal/router"
+	"github.com/kami/maven/internal/tool"
+	"github.com/kami/maven/internal/voice"
+)
+
+// TestApplyAction_FactCapture_QueuesEntityResolution covers the wiring from
+// Vikunja #279: a voice-tapped fact's key doubles as its entity-resolution
+// subject, so writing a fact through applyAction (not directly through the
+// store) must leave it in the fact-enrichment pending queue.
+func TestApplyAction_FactCapture_QueuesEntityResolution(t *testing.T) {
+	ctx := context.Background()
+	st := newTestStore(t)
+	api := ipc.NewStoreAPI(st)
+	now := time.Now()
+
+	emb := router.NewHashEmbedder(1024)
+	matcher := tool.NewMatcher(api)
+	rtr := buildRouter(emb, matcher, 0.55, nil)
+
+	h := &reactiveHandler{
+		api:       api,
+		embedder:  emb,
+		router:    rtr,
+		replier:   voice.NewStubReplier(),
+		now:       func() time.Time { return now },
+		memStore:  memory.NewInMemoryStore(),
+		dataStore: st,
+	}
+
+	dec := router.Decision{
+		Intent: router.IntentFact,
+		Slots:  router.Slots{Key: "the espresso machine", HasKey: true, Value: `"needs descaling"`},
+	}
+	h.applyAction(ctx, dec)
+
+	pending, err := st.PendingFactResolutions(ctx, 10)
+	if err != nil {
+		t.Fatalf("PendingFactResolutions: %v", err)
+	}
+	if len(pending) != 1 {
+		t.Fatalf("expected 1 fact queued for entity resolution, got %d: %+v", len(pending), pending)
+	}
+	if pending[0].Subject != "the espresso machine" {
+		t.Fatalf("expected subject to carry the fact key, got %q", pending[0].Subject)
+	}
+}

cmd/mavend/voice.go

@@ -550,6 +550,13 @@ func (h *reactiveHandler) applyAction(ctx context.Context, dec router.Decision)
 			Value:      dec.Slots.Value,
 			Source:     "tap:voice",
 			Confidence: 1.0,
+			// Subject: the key doubles as the entity-resolution candidate —
+			// a voice-tapped fact's key is usually the thing/person it's
+			// about ("espresso_machine", "kate"), so queueing it for Nexus
+			// resolution costs one async lookup and is a no-op (not_found)
+			// for the abstract self-state keys (mood, water) that aren't
+			// entities at all.
+			Subject: dec.Slots.Key,
 		}
 		factID, err := h.api.WriteFact(ctx, req)
 		if err != nil {