No deadline survives the turn path, from mavweb down to llama-server (#188)

Co-authored-by: claude <no-reply@agents.claude.kvmx.ru>
Co-committed-by: claude <no-reply@agents.claude.kvmx.ru>

cmd/mavend/clarify.go

@@ -571,7 +571,7 @@ func (h *reactiveHandler) finishClarified(ctx context.Context, dec router.Decisi
 	}
 	reply := h.applyAction(ctx, dec)
 	if reply == "" {
-		reply = h.replier.Reply(dec)
+		reply = h.replier.Reply(ctx, dec)
 	}
 	if reply == "" {
 		// Belt: an empty reply here would be a silent drop.

cmd/mavend/replier_llm.go

@@ -22,7 +22,7 @@ func newLLMReplier(c phraser.Completer, block func() string) *llmReplier {
 
 // Reply never fails: a clarify, a model error and an unusable generation all
 // answer from the stub, which is what keeps a turn from breaking on the model.
-func (r *llmReplier) Reply(d router.Decision) string {
+func (r *llmReplier) Reply(ctx context.Context, d router.Decision) string {
 	if d.Clarify {
 		// The deck, not the stub's single sentence: a clarify she cannot turn
 		// into a question is the line he hears most often when she misses him,
@@ -39,14 +39,14 @@ func (r *llmReplier) Reply(d router.Decision) string {
 		// что ты выпел стакан воды" for "я выпил воды".
 		return phraser.FactAck(d.Utterance)
 	}
-	out, err := r.p.PhraseReply(context.Background(), d)
+	out, err := r.p.PhraseReply(ctx, d)
 	if err != nil || out == "" {
-		return r.stub.Reply(d)
+		return r.stub.Reply(ctx, 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 r.stub.Reply(ctx, d)
 	}
 	return out
 }

cmd/mavend/replier_llm_test.go

@@ -22,7 +22,7 @@ func (s stubCompleter) Complete(_ context.Context, _ llm.Req) (string, error) {
 
 func TestLLMReplierPassesTheModelReplyThrough(t *testing.T) {
 	r := newLLMReplier(stubCompleter{out: `{"response":"записала, кофе закончился","mood":"neutral"}`}, nil)
-	got := r.Reply(router.Decision{Intent: router.IntentNote, Slots: router.Slots{Text: "кофе закончился"}})
+	got := r.Reply(context.Background(), router.Decision{Intent: router.IntentNote, Slots: router.Slots{Text: "кофе закончился"}})
 	if got != "записала, кофе закончился" {
 		t.Errorf("got %q, want %q", got, "записала, кофе закончился")
 	}
@@ -42,7 +42,7 @@ func TestLLMReplierFallsBackToStubOnEmpty(t *testing.T) {
 // the clarify deck rather than the stub's single sentence.
 func TestLLMReplierClarifyReadsTheDeck(t *testing.T) {
 	r := newLLMReplier(stubCompleter{out: "я всё поняла"}, nil)
-	got := r.Reply(router.Decision{Clarify: true, Utterance: "мгм"})
+	got := r.Reply(context.Background(), router.Decision{Clarify: true, Utterance: "мгм"})
 	if got == "я всё поняла" {
 		t.Fatal("a clarify must not be phrased by the model")
 	}
@@ -50,7 +50,7 @@ func TestLLMReplierClarifyReadsTheDeck(t *testing.T) {
 		t.Errorf("on clarify: got %q, want %q", got, want)
 	}
 	// Two different misses do not sound identical.
-	if same := r.Reply(router.Decision{Clarify: true, Utterance: "а"}); same == got {
+	if same := r.Reply(context.Background(), router.Decision{Clarify: true, Utterance: "а"}); same == got {
 		t.Log("two utterances hashed to the same line, which is allowed but should be rare")
 	}
 }
@@ -60,14 +60,14 @@ func TestLLMReplierClarifyReadsTheDeck(t *testing.T) {
 // produce, which is the same claim without pinning one wording.
 func assertAck(t *testing.T, r *llmReplier, d router.Decision, key, what string) {
 	t.Helper()
-	if got := r.Reply(d); !phraser.IsAck(key, nil, got) {
+	if got := r.Reply(context.Background(), d); !phraser.IsAck(key, nil, got) {
 		t.Errorf("on %s: got %q, want a %q line", what, got, key)
 	}
 }
 
 func assertStub(t *testing.T, r *llmReplier, d router.Decision, what string) {
 	t.Helper()
-	got, want := r.Reply(d), voice.NewStubReplier().Reply(d)
+	got, want := r.Reply(context.Background(), d), voice.NewStubReplier().Reply(context.Background(), d)
 	if got != want {
 		t.Errorf("on %s: got %q, want stub %q", what, got, want)
 	}

cmd/mavend/voice.go

@@ -458,7 +458,7 @@ func (h *reactiveHandler) runTurn(ctx context.Context, text string, src turnSour
 
 	// 9. replier — phrase the reply across the router decision.
 	if replyText == "" {
-		replyText = h.replier.Reply(dec)
+		replyText = h.replier.Reply(ctx, dec)
 	}
 	return withNotice(expiredNotice, replyText)
 }

cmd/mavweb/main.go

@@ -58,6 +58,12 @@ func main() {
 	// mutex, so sharing the connection would freeze every other page for the
 	// length of the load. See handleModels.
 	var swapConn modelController
+	// turnConn — a third connection, for POST /api/chat and nothing else, for
+	// the same reason /models has one (V-638). A chat turn routes, phrases and
+	// may act, bounded only by phraser.timeout at 60s, and every other handler
+	// on this server queues behind it on the shared client's one mutex. Nil ⇒
+	// chat shares the main connection, which is how it behaved before.
+	var turnConn ipc.CoreAPI
 	if *coreSock != "" {
 		c, err := ipc.DialWait(*coreSock, 60*time.Second)
 		if err != nil {
@@ -71,6 +77,12 @@ func main() {
 			defer sc.Close()
 			swapConn = sc
 		}
+		if tc, err := ipc.Dial(*coreSock); err != nil {
+			log.Printf("chat: third core connection failed (%v) — /api/chat will share the main one and a turn will block the other pages", err)
+		} else {
+			defer tc.Close()
+			turnConn = tc
+		}
 	}
 
 	// stepUpSession stays nil unless the passkey endpoints are wired below — it
@@ -208,7 +220,13 @@ func main() {
 	// decides how every utterance is routed and how every reply is worded.
 	mux.HandleFunc("/tools", gatedPage(handleTools))
 	mux.HandleFunc("/routines", gatedPage(handleRoutines))
-	mux.HandleFunc("/api/chat", gatedPage(handleChatAPI))
+	mux.HandleFunc("/api/chat", func(w http.ResponseWriter, r *http.Request) {
+		c := turnConn
+		if c == nil {
+			c = core
+		}
+		handleChatAPI(w, r, c, stepUpSession, *requireStepUp)
+	})
 	mux.HandleFunc("/api/revert", gatedPage(handleRevert))
 	mux.HandleFunc("/api/correct", gatedPage(handleCorrectAPI))
 	mux.HandleFunc("/models", func(w http.ResponseWriter, r *http.Request) {