Merge pull request #935 from putueddy/feat/telegram-chunking

feat: add message chunking in Telegram Send method
2026-06-12 18:08:54 +00:00 · 2026-03-07 23:47:06 +08:00
parent 66e6fb6c79 f07dbd1db2
commit 826f92cf53
2 changed files with 313 additions and 5 deletions
@@ -88,7 +88,7 @@ func NewTelegramChannel(cfg *config.Config, bus *bus.MessageBus) (*TelegramChann
 		telegramCfg,
 		bus,
 		telegramCfg.AllowFrom,
-		channels.WithMaxMessageLength(4096),
+		channels.WithMaxMessageLength(4000),
 		channels.WithGroupTrigger(telegramCfg.GroupTrigger),
 		channels.WithReasoningChannelID(telegramCfg.ReasoningChannelID),
 	)
@@ -173,22 +173,57 @@ func (c *TelegramChannel) Send(ctx context.Context, msg bus.OutboundMessage) err
 		return fmt.Errorf("invalid chat ID %s: %w", msg.ChatID, channels.ErrSendFailed)
 	}

-	htmlContent := markdownToTelegramHTML(msg.Content)
+	if msg.Content == "" {
+		return nil
+	}

-	// Typing/placeholder handled by Manager.preSend — just send the message
+	// The Manager already splits messages to ≤4000 chars (WithMaxMessageLength),
+	// so msg.Content is guaranteed to be within that limit. We still need to
+	// check if HTML expansion pushes it beyond Telegram's 4096-char API limit.
+	queue := []string{msg.Content}
+	for len(queue) > 0 {
+		chunk := queue[0]
+		queue = queue[1:]
+
+		htmlContent := markdownToTelegramHTML(chunk)
+
+		if len([]rune(htmlContent)) > 4096 {
+			ratio := float64(len([]rune(chunk))) / float64(len([]rune(htmlContent)))
+			smallerLen := int(float64(4096) * ratio * 0.95) // 5% safety margin
+			if smallerLen < 100 {
+				smallerLen = 100
+			}
+			// Push sub-chunks back to the front of the queue for
+			// re-validation instead of sending them blindly.
+			subChunks := channels.SplitMessage(chunk, smallerLen)
+			queue = append(subChunks, queue...)
+			continue
+		}
+
+		if err := c.sendHTMLChunk(ctx, chatID, htmlContent, chunk); err != nil {
+			return err
+		}
+	}
+
+	return nil
+}
+
+// sendHTMLChunk sends a single HTML message, falling back to the original
+// markdown as plain text on parse failure so users never see raw HTML tags.
+func (c *TelegramChannel) sendHTMLChunk(ctx context.Context, chatID int64, htmlContent, mdFallback string) error {
 	tgMsg := tu.Message(tu.ID(chatID), htmlContent)
 	tgMsg.ParseMode = telego.ModeHTML

-	if _, err = c.bot.SendMessage(ctx, tgMsg); err != nil {
+	if _, err := c.bot.SendMessage(ctx, tgMsg); err != nil {
 		logger.ErrorCF("telegram", "HTML parse failed, falling back to plain text", map[string]any{
 			"error": err.Error(),
 		})
+		tgMsg.Text = mdFallback
 		tgMsg.ParseMode = ""
 		if _, err = c.bot.SendMessage(ctx, tgMsg); err != nil {
 			return fmt.Errorf("telegram send: %w", channels.ErrTemporary)
 		}
 	}
-
 	return nil
 }

@@ -0,0 +1,273 @@
+package telegram
+
+import (
+	"context"
+	"encoding/json"
+	"errors"
+	"strings"
+	"testing"
+
+	"github.com/mymmrac/telego"
+	ta "github.com/mymmrac/telego/telegoapi"
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+
+	"github.com/sipeed/picoclaw/pkg/bus"
+	"github.com/sipeed/picoclaw/pkg/channels"
+)
+
+const testToken = "1234567890:aaaabbbbaaaabbbbaaaabbbbaaaabbbbccc"
+
+// stubCaller implements ta.Caller for testing.
+type stubCaller struct {
+	calls  []stubCall
+	callFn func(ctx context.Context, url string, data *ta.RequestData) (*ta.Response, error)
+}
+
+type stubCall struct {
+	URL  string
+	Data *ta.RequestData
+}
+
+func (s *stubCaller) Call(ctx context.Context, url string, data *ta.RequestData) (*ta.Response, error) {
+	s.calls = append(s.calls, stubCall{URL: url, Data: data})
+	return s.callFn(ctx, url, data)
+}
+
+// stubConstructor implements ta.RequestConstructor for testing.
+type stubConstructor struct{}
+
+func (s *stubConstructor) JSONRequest(parameters any) (*ta.RequestData, error) {
+	return &ta.RequestData{}, nil
+}
+
+func (s *stubConstructor) MultipartRequest(
+	parameters map[string]string,
+	files map[string]ta.NamedReader,
+) (*ta.RequestData, error) {
+	return &ta.RequestData{}, nil
+}
+
+// successResponse returns a ta.Response that telego will treat as a successful SendMessage.
+func successResponse(t *testing.T) *ta.Response {
+	t.Helper()
+	msg := &telego.Message{MessageID: 1}
+	b, err := json.Marshal(msg)
+	require.NoError(t, err)
+	return &ta.Response{Ok: true, Result: b}
+}
+
+// newTestChannel creates a TelegramChannel with a mocked bot for unit testing.
+func newTestChannel(t *testing.T, caller *stubCaller) *TelegramChannel {
+	t.Helper()
+
+	bot, err := telego.NewBot(testToken,
+		telego.WithAPICaller(caller),
+		telego.WithRequestConstructor(&stubConstructor{}),
+		telego.WithDiscardLogger(),
+	)
+	require.NoError(t, err)
+
+	base := channels.NewBaseChannel("telegram", nil, nil, nil,
+		channels.WithMaxMessageLength(4000),
+	)
+	base.SetRunning(true)
+
+	return &TelegramChannel{
+		BaseChannel: base,
+		bot:         bot,
+		chatIDs:     make(map[string]int64),
+	}
+}
+
+func TestSend_EmptyContent(t *testing.T) {
+	caller := &stubCaller{
+		callFn: func(ctx context.Context, url string, data *ta.RequestData) (*ta.Response, error) {
+			t.Fatal("SendMessage should not be called for empty content")
+			return nil, nil
+		},
+	}
+	ch := newTestChannel(t, caller)
+
+	err := ch.Send(context.Background(), bus.OutboundMessage{
+		ChatID:  "12345",
+		Content: "",
+	})
+
+	assert.NoError(t, err)
+	assert.Empty(t, caller.calls, "no API calls should be made for empty content")
+}
+
+func TestSend_ShortMessage_SingleCall(t *testing.T) {
+	caller := &stubCaller{
+		callFn: func(ctx context.Context, url string, data *ta.RequestData) (*ta.Response, error) {
+			return successResponse(t), nil
+		},
+	}
+	ch := newTestChannel(t, caller)
+
+	err := ch.Send(context.Background(), bus.OutboundMessage{
+		ChatID:  "12345",
+		Content: "Hello, world!",
+	})
+
+	assert.NoError(t, err)
+	assert.Len(t, caller.calls, 1, "short message should result in exactly one SendMessage call")
+}
+
+func TestSend_LongMessage_SingleCall(t *testing.T) {
+	// With WithMaxMessageLength(4000), the Manager pre-splits messages before
+	// they reach Send(). A message at exactly 4000 chars should go through
+	// as a single SendMessage call (no re-split needed since HTML expansion
+	// won't exceed 4096 for plain text).
+	caller := &stubCaller{
+		callFn: func(ctx context.Context, url string, data *ta.RequestData) (*ta.Response, error) {
+			return successResponse(t), nil
+		},
+	}
+	ch := newTestChannel(t, caller)
+
+	longContent := strings.Repeat("a", 4000)
+
+	err := ch.Send(context.Background(), bus.OutboundMessage{
+		ChatID:  "12345",
+		Content: longContent,
+	})
+
+	assert.NoError(t, err)
+	assert.Len(t, caller.calls, 1, "pre-split message within limit should result in one SendMessage call")
+}
+
+func TestSend_HTMLFallback_PerChunk(t *testing.T) {
+	callCount := 0
+	caller := &stubCaller{
+		callFn: func(ctx context.Context, url string, data *ta.RequestData) (*ta.Response, error) {
+			callCount++
+			// Fail on odd calls (HTML attempt), succeed on even calls (plain text fallback)
+			if callCount%2 == 1 {
+				return nil, errors.New("Bad Request: can't parse entities")
+			}
+			return successResponse(t), nil
+		},
+	}
+	ch := newTestChannel(t, caller)
+
+	err := ch.Send(context.Background(), bus.OutboundMessage{
+		ChatID:  "12345",
+		Content: "Hello **world**",
+	})
+
+	assert.NoError(t, err)
+	// One short message → 1 HTML attempt (fail) + 1 plain text fallback (success) = 2 calls
+	assert.Equal(t, 2, len(caller.calls), "should have HTML attempt + plain text fallback")
+}
+
+func TestSend_HTMLFallback_BothFail(t *testing.T) {
+	caller := &stubCaller{
+		callFn: func(ctx context.Context, url string, data *ta.RequestData) (*ta.Response, error) {
+			return nil, errors.New("send failed")
+		},
+	}
+	ch := newTestChannel(t, caller)
+
+	err := ch.Send(context.Background(), bus.OutboundMessage{
+		ChatID:  "12345",
+		Content: "Hello",
+	})
+
+	assert.Error(t, err)
+	assert.True(t, errors.Is(err, channels.ErrTemporary), "error should wrap ErrTemporary")
+	assert.Equal(t, 2, len(caller.calls), "should have HTML attempt + plain text attempt")
+}
+
+func TestSend_LongMessage_HTMLFallback_StopsOnError(t *testing.T) {
+	// With a long message that gets split into 2 chunks, if both HTML and
+	// plain text fail on the first chunk, Send should return early.
+	caller := &stubCaller{
+		callFn: func(ctx context.Context, url string, data *ta.RequestData) (*ta.Response, error) {
+			return nil, errors.New("send failed")
+		},
+	}
+	ch := newTestChannel(t, caller)
+
+	longContent := strings.Repeat("x", 4001)
+
+	err := ch.Send(context.Background(), bus.OutboundMessage{
+		ChatID:  "12345",
+		Content: longContent,
+	})
+
+	assert.Error(t, err)
+	// Should fail on the first chunk (2 calls: HTML + fallback), never reaching the second chunk.
+	assert.Equal(t, 2, len(caller.calls), "should stop after first chunk fails both HTML and plain text")
+}
+
+func TestSend_MarkdownShortButHTMLLong_MultipleCalls(t *testing.T) {
+	caller := &stubCaller{
+		callFn: func(ctx context.Context, url string, data *ta.RequestData) (*ta.Response, error) {
+			return successResponse(t), nil
+		},
+	}
+	ch := newTestChannel(t, caller)
+
+	// Create markdown whose length is <= 4000 but whose HTML expansion is much longer.
+	// "**a** " (6 chars) becomes "<b>a</b> " (9 chars) in HTML, so repeating it many times
+	// yields HTML that exceeds Telegram's limit while markdown stays within it.
+	markdownContent := strings.Repeat("**a** ", 600) // 3600 chars markdown, HTML ~5400+ chars
+	assert.LessOrEqual(t, len([]rune(markdownContent)), 4000, "markdown content must not exceed chunk size")
+
+	htmlExpanded := markdownToTelegramHTML(markdownContent)
+	assert.Greater(
+		t, len([]rune(htmlExpanded)), 4096,
+		"HTML expansion must exceed Telegram limit for this test to be meaningful",
+	)
+
+	err := ch.Send(context.Background(), bus.OutboundMessage{
+		ChatID:  "12345",
+		Content: markdownContent,
+	})
+
+	assert.NoError(t, err)
+	assert.Greater(
+		t, len(caller.calls), 1,
+		"markdown-short but HTML-long message should be split into multiple SendMessage calls",
+	)
+}
+
+func TestSend_NotRunning(t *testing.T) {
+	caller := &stubCaller{
+		callFn: func(ctx context.Context, url string, data *ta.RequestData) (*ta.Response, error) {
+			t.Fatal("should not be called")
+			return nil, nil
+		},
+	}
+	ch := newTestChannel(t, caller)
+	ch.SetRunning(false)
+
+	err := ch.Send(context.Background(), bus.OutboundMessage{
+		ChatID:  "12345",
+		Content: "Hello",
+	})
+
+	assert.ErrorIs(t, err, channels.ErrNotRunning)
+	assert.Empty(t, caller.calls)
+}
+
+func TestSend_InvalidChatID(t *testing.T) {
+	caller := &stubCaller{
+		callFn: func(ctx context.Context, url string, data *ta.RequestData) (*ta.Response, error) {
+			t.Fatal("should not be called")
+			return nil, nil
+		},
+	}
+	ch := newTestChannel(t, caller)
+
+	err := ch.Send(context.Background(), bus.OutboundMessage{
+		ChatID:  "not-a-number",
+		Content: "Hello",
+	})
+
+	assert.Error(t, err)
+	assert.True(t, errors.Is(err, channels.ErrSendFailed), "error should wrap ErrSendFailed")
+	assert.Empty(t, caller.calls)
+}