fix(llm): send generous max_tokens on every request

The copied OpenAI-compatible client sent no max_tokens. Thinking models
(qwen3, deepseek-r1) spend their budget on the reasoning trace and return
EMPTY content when max_tokens is unset, which the summarizer treats as an
error. ADR-004 says change Tapir's copy rather than the hyperguild upstream,
so set a generous default (8192) leaving room for both reasoning and output.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

internal/adapters/llm/client_test.go

@@ -43,6 +43,27 @@ func TestClient_Complete(t *testing.T) {
 	}
 }
 
+// TestClient_SendsMaxTokens guards Tapir's ADR-004 change to the copied client:
+// it MUST send a positive max_tokens, or thinking models return empty content.
+func TestClient_SendsMaxTokens(t *testing.T) {
+	var body chatRequest
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		_ = json.NewDecoder(r.Body).Decode(&body)
+		_ = json.NewEncoder(w).Encode(map[string]any{
+			"choices": []map[string]any{{"message": map[string]any{"content": "ok"}}},
+		})
+	}))
+	defer srv.Close()
+
+	c := New(srv.URL, "", "test-model", 10*time.Second)
+	if _, err := c.Complete(context.Background(), "sys", "user"); err != nil {
+		t.Fatalf("Complete: %v", err)
+	}
+	if body.MaxTokens <= 0 {
+		t.Errorf("max_tokens = %d, want > 0 (thinking models return empty content without it)", body.MaxTokens)
+	}
+}
+
 func TestClient_ReturnsErrorOnNon200(t *testing.T) {
 	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
 		http.Error(w, "overloaded", http.StatusServiceUnavailable)