test(message): cover pico and weixin media text semantics

pkg/channels/pico/pico_test.go

@@ -835,6 +835,75 @@ func TestSendMedia_DismissesTrackedToolFeedbackMessage(t *testing.T) {
 	}
 }
 
+func TestSendMedia_IncludesCaptionAndAttachmentsInSinglePayload(t *testing.T) {
+	ch := newTestPicoChannel(t)
+	store := media.NewFileMediaStore()
+	ch.SetMediaStore(store)
+
+	if err := ch.Start(context.Background()); err != nil {
+		t.Fatalf("Start() error = %v", err)
+	}
+	defer ch.Stop(context.Background())
+
+	clientConn, received, cleanup := newTestPicoWebSocket(t)
+	defer cleanup()
+	ch.addConnForTest(&picoConn{id: "conn-1", conn: clientConn, sessionID: "sess-1"})
+
+	localPath := filepath.Join(t.TempDir(), "photo.png")
+	if err := os.WriteFile(localPath, []byte("png-body"), 0o600); err != nil {
+		t.Fatalf("WriteFile() error = %v", err)
+	}
+
+	ref, err := store.Store(localPath, media.MediaMeta{
+		Filename:    "photo.png",
+		ContentType: "image/png",
+	}, "test-scope")
+	if err != nil {
+		t.Fatalf("Store() error = %v", err)
+	}
+
+	_, err = ch.SendMedia(context.Background(), bus.OutboundMediaMessage{
+		ChatID: "pico:sess-1",
+		Parts: []bus.MediaPart{{
+			Ref:         ref,
+			Type:        "image",
+			Filename:    "photo.png",
+			ContentType: "image/png",
+			Caption:     "recipe translation",
+		}},
+	})
+	if err != nil {
+		t.Fatalf("SendMedia() error = %v", err)
+	}
+
+	select {
+	case msg := <-received:
+		if msg.Type != TypeMessageCreate {
+			t.Fatalf("message type = %q, want %q", msg.Type, TypeMessageCreate)
+		}
+		payload := msg.Payload
+		if got := payload[PayloadKeyContent]; got != "recipe translation" {
+			t.Fatalf("content = %#v, want %q", got, "recipe translation")
+		}
+		rawAttachments, ok := payload["attachments"].([]any)
+		if !ok || len(rawAttachments) != 1 {
+			t.Fatalf("attachments = %#v, want 1 attachment", payload["attachments"])
+		}
+		attachment, ok := rawAttachments[0].(map[string]any)
+		if !ok {
+			t.Fatalf("attachment = %#v, want map", rawAttachments[0])
+		}
+		if got := attachment["type"]; got != "image" {
+			t.Fatalf("attachment type = %#v, want image", got)
+		}
+		if got := attachment["filename"]; got != "photo.png" {
+			t.Fatalf("attachment filename = %#v, want photo.png", got)
+		}
+	case <-time.After(time.Second):
+		t.Fatal("expected media payload to be delivered")
+	}
+}
+
 func TestPicoDownloadURLForRef(t *testing.T) {
 	got, err := picoDownloadURLForRef("media://attachment-1")
 	if err != nil {

pkg/channels/weixin/weixin_test.go

@@ -4,6 +4,7 @@ import (
 	"bytes"
 	"context"
 	"encoding/base64"
+	"encoding/json"
 	"errors"
 	"io"
 	"net/http"
@@ -319,3 +320,61 @@ func TestSelectInboundMediaItemFallsBackToRefMessage(t *testing.T) {
 		t.Fatalf("selectInboundMediaItem().Type = %d, want %d", item.Type, MessageItemTypeImage)
 	}
 }
+
+func TestSendUploadedMedia_SendsCaptionAsSeparateTextBeforeMedia(t *testing.T) {
+	var requests []SendMessageReq
+	ch := &WeixinChannel{
+		api: &ApiClient{
+			BaseURL: "https://ilinkai.weixin.qq.com/",
+			HttpClient: &http.Client{Transport: roundTripFunc(func(r *http.Request) (*http.Response, error) {
+				if r.URL.Path != "/ilink/bot/sendmessage" {
+					t.Fatalf("sendmessage path = %q, want /ilink/bot/sendmessage", r.URL.Path)
+				}
+				var req SendMessageReq
+				if err := json.NewDecoder(r.Body).Decode(&req); err != nil {
+					t.Fatalf("decode sendmessage req: %v", err)
+				}
+				requests = append(requests, req)
+				return &http.Response{
+					StatusCode: http.StatusOK,
+					Body:       io.NopCloser(bytes.NewReader([]byte(`{"ret":0,"errcode":0}`))),
+					Header:     make(http.Header),
+				}, nil
+			})},
+		},
+		typingCache: make(map[string]typingTicketCacheEntry),
+	}
+
+	err := ch.sendUploadedMedia(
+		context.Background(),
+		"user-1",
+		"ctx-1",
+		"recipe translation",
+		UploadMediaTypeImage,
+		&uploadedFileInfo{
+			downloadParam: "download-token",
+			aesKeyHex:     "31323334353637383930616263646566",
+			fileSize:      11,
+			cipherSize:    16,
+			filename:      "photo.png",
+		},
+	)
+	if err != nil {
+		t.Fatalf("sendUploadedMedia() error = %v", err)
+	}
+	if len(requests) != 2 {
+		t.Fatalf("sendUploadedMedia() sent %d requests, want 2", len(requests))
+	}
+	if len(requests[0].Msg.ItemList) != 1 || requests[0].Msg.ItemList[0].Type != MessageItemTypeText {
+		t.Fatalf("first request item = %+v, want text item", requests[0].Msg.ItemList)
+	}
+	if got := requests[0].Msg.ItemList[0].TextItem.Text; got != "recipe translation" {
+		t.Fatalf("first request text = %q, want recipe translation", got)
+	}
+	if len(requests[1].Msg.ItemList) != 1 || requests[1].Msg.ItemList[0].Type != MessageItemTypeImage {
+		t.Fatalf("second request item = %+v, want image item", requests[1].Msg.ItemList)
+	}
+	if requests[1].Msg.ItemList[0].ImageItem == nil || requests[1].Msg.ItemList[0].ImageItem.Media == nil {
+		t.Fatalf("second request image media = %+v, want media ref", requests[1].Msg.ItemList[0].ImageItem)
+	}
+}