internal/adapters/llm/bodycap_test.go

@@ -79,3 +79,78 @@ func TestClient_AFailingBodyIsReadOnlyUpToTheErrorBound(t *testing.T) {
 		t.Fatalf("the client kept reading an endless error body: took %s", time.Since(start))
 	}
 }
+
+// sizedGateway answers 200 with a valid completion padded with trailing whitespace to
+// exactly size bytes, so the boundary of the cap can be probed to the byte.
+func sizedGateway(t *testing.T, size int) *httptest.Server {
+	t.Helper()
+	const base = `{"choices":[{"message":{"content":"ok"}}]}`
+	payload := base + strings.Repeat(" ", size-len(base))
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {
+		w.Header().Set("Content-Type", "application/json")
+		_, _ = w.Write([]byte(payload))
+	}))
+	t.Cleanup(srv.Close)
+	return srv
+}
+
+func TestClient_ABodyOfExactlyTheCapIsReadAndOneByteMoreIsRefused(t *testing.T) {
+	const capBytes = 4096
+	for _, tt := range []struct {
+		name    string
+		size    int
+		wantErr bool
+	}{
+		{"one under", capBytes - 1, false},
+		{"exactly the cap", capBytes, false},
+		{"one over", capBytes + 1, true},
+	} {
+		t.Run(tt.name, func(t *testing.T) {
+			c := New(sizedGateway(t, tt.size).URL, "", "m", 5*time.Second, WithMaxResponseBytes(capBytes))
+
+			got, err := c.Complete(context.Background(), "s", "u")
+
+			if tt.wantErr {
+				if err == nil || !strings.Contains(err.Error(), "exceeds") {
+					t.Fatalf("want a response-too-large error, got %q, %v", got, err)
+				}
+				return
+			}
+			if err != nil || got != "ok" {
+				t.Fatalf("want ok, got %q, %v", got, err)
+			}
+		})
+	}
+}
+
+// New is what production calls: no option. The default is therefore the live bound.
+func TestClient_TheDefaultCapIsEightMiBWhenNoOptionIsGiven(t *testing.T) {
+	for _, tt := range []struct {
+		name    string
+		size    int
+		wantErr bool
+	}{
+		{"exactly 8 MiB", 8 << 20, false},
+		{"8 MiB plus one", 8<<20 + 1, true},
+	} {
+		t.Run(tt.name, func(t *testing.T) {
+			c := New(sizedGateway(t, tt.size).URL, "", "m", 10*time.Second)
+
+			_, err := c.Complete(context.Background(), "s", "u")
+
+			if (err != nil) != tt.wantErr {
+				t.Fatalf("size %d: err = %v, wantErr %v", tt.size, err, tt.wantErr)
+			}
+		})
+	}
+}
+
+func TestClient_ANonPositiveCapOptionKeepsTheDefault(t *testing.T) {
+	for _, n := range []int64{0, -1} {
+		c := New(sizedGateway(t, 1024).URL, "", "m", 5*time.Second, WithMaxResponseBytes(n))
+
+		if got, err := c.Complete(context.Background(), "s", "u"); err != nil || got != "ok" {
+			t.Fatalf("WithMaxResponseBytes(%d): want ok from the default cap, got %q, %v", n, got, err)
+		}
+	}
+}

internal/adapters/llm/client.go

@@ -202,6 +202,7 @@ func (c *Client) Complete(ctx context.Context, system, user string) (string, err
 
 	if resp.StatusCode != http.StatusOK {
 		// Only the bounded head is ever used (HTTPError.Error truncates to it), so read no more.
+		// A read error here only shortens a diagnostic; the status code below is what callers act on.
 		head, _ := io.ReadAll(io.LimitReader(resp.Body, maxErrorBody+1))
 		return "", &HTTPError{Code: resp.StatusCode, Body: string(head)}
 	}