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

internal/ipc/api.go

@@ -84,6 +84,13 @@ type WriteFactReq struct {
 	Source     string    `json:"source"`
 	Confidence float64   `json:"confidence"`
 	VoidsID    *int64    `json:"voids_id,omitempty"`
+
+	// Subject — free-text "who/what this fact is about" (e.g. "the espresso
+	// machine", "Kate"). Empty (the default, so old callers are unaffected)
+	// means the fact isn't about a resolvable entity. When set, the fact
+	// enrichment worker (cmd/mavend/factenrichment.go) later resolves it
+	// against Nexus into an entity_id — see Vikunja #279.
+	Subject string `json:"subject,omitempty"`
 }
 
 // idReq — methods keyed by a single id.

internal/ipc/server.go

@@ -36,7 +36,7 @@ func (a *storeAPI) WriteFact(ctx context.Context, req WriteFactReq) (int64, erro
 	if req.VoidsID != nil {
 		voids = sql.NullInt64{Int64: *req.VoidsID, Valid: true}
 	}
-	id, err := a.s.WriteFact(ctx, req.Ts, store.FactKind(req.Kind), req.Key, req.Value, req.Source, req.Confidence, voids)
+	id, err := a.s.WriteFactAboutSubject(ctx, req.Ts, store.FactKind(req.Kind), req.Key, req.Subject, req.Value, req.Source, req.Confidence, voids)
 	return id, mapErr(err)
 }