Feat: Discord message length check and auto split

pkg/channels/base_test.go

@@ -50,4 +50,3 @@ func TestBaseChannelIsAllowed(t *testing.T) {
 		})
 	}
 }
-

pkg/channels/discord.go

@@ -4,6 +4,7 @@ import (
 	"context"
 	"fmt"
 	"os"
+	"strings"
 	"time"
 
 	"github.com/bwmarrin/discordgo"
@@ -100,15 +101,156 @@ func (c *DiscordChannel) Send(ctx context.Context, msg bus.OutboundMessage) erro
 		return fmt.Errorf("channel ID is empty")
 	}
 
-	message := msg.Content
+	runes := []rune(msg.Content)
+	if len(runes) == 0 {
+		return nil
+	}
+
+	chunks := splitMessage(msg.Content, 1500) // Discord has a limit of 2000 characters per message, leave 500 for natural split e.g. code blocks
+
+	for _, chunk := range chunks {
+		if err := c.sendChunk(ctx, channelID, chunk); err != nil {
+			return err
+		}
+	}
+
+	return nil
+}
+
+// splitMessage splits long messages into chunks, preserving code block integrity
+// Uses natural boundaries (newlines, spaces) and extends messages slightly to avoid breaking code blocks
+func splitMessage(content string, limit int) []string {
+	var messages []string
+
+	for len(content) > 0 {
+		if len(content) <= limit {
+			messages = append(messages, content)
+			break
+		}
+
+		msgEnd := limit
+
+		// Find natural split point within the limit
+		msgEnd = findLastNewline(content[:limit], 200)
+		if msgEnd <= 0 {
+			msgEnd = findLastSpace(content[:limit], 100)
+		}
+		if msgEnd <= 0 {
+			msgEnd = limit
+		}
+
+		// Check if this would end with an incomplete code block
+		candidate := content[:msgEnd]
+		unclosedIdx := findLastUnclosedCodeBlock(candidate)
+
+		if unclosedIdx >= 0 {
+			// Message would end with incomplete code block
+			// Try to extend to include the closing ``` (with some buffer)
+			extendedLimit := limit + 500 // Allow 500 char buffer for code blocks
+			if len(content) > extendedLimit {
+				closingIdx := findNextClosingCodeBlock(content, msgEnd)
+				if closingIdx > 0 && closingIdx <= extendedLimit {
+					// Extend to include the closing ```
+					msgEnd = closingIdx
+				} else {
+					// Can't find closing, split before the code block
+					msgEnd = findLastNewline(content[:unclosedIdx], 200)
+					if msgEnd <= 0 {
+						msgEnd = findLastSpace(content[:unclosedIdx], 100)
+					}
+					if msgEnd <= 0 {
+						msgEnd = unclosedIdx
+					}
+				}
+			} else {
+				// Remaining content fits within extended limit
+				msgEnd = len(content)
+			}
+		}
+
+		if msgEnd <= 0 {
+			msgEnd = limit
+		}
+
+		messages = append(messages, content[:msgEnd])
+		content = strings.TrimSpace(content[msgEnd:])
+	}
+
+	return messages
+}
+
+// findLastUnclosedCodeBlock finds the last opening ``` that doesn't have a closing ```
+// Returns the position of the opening ``` or -1 if all code blocks are complete
+func findLastUnclosedCodeBlock(text string) int {
+	count := 0
+	lastOpenIdx := -1
+
+	for i := 0; i < len(text); i++ {
+		if i+2 < len(text) && text[i] == '`' && text[i+1] == '`' && text[i+2] == '`' {
+			if count == 0 {
+				lastOpenIdx = i
+			}
+			count++
+			i += 2
+		}
+	}
+
+	// If odd number of ``` markers, last one is unclosed
+	if count%2 == 1 {
+		return lastOpenIdx
+	}
+	return -1
+}
+
+// findNextClosingCodeBlock finds the next closing ``` starting from a position
+// Returns the position after the closing ``` or -1 if not found
+func findNextClosingCodeBlock(text string, startIdx int) int {
+	for i := startIdx; i < len(text); i++ {
+		if i+2 < len(text) && text[i] == '`' && text[i+1] == '`' && text[i+2] == '`' {
+			return i + 3
+		}
+	}
+	return -1
+}
+
+// findLastNewline finds the last newline character within the last N characters
+// Returns the position of the newline or -1 if not found
+func findLastNewline(s string, searchWindow int) int {
+	searchStart := len(s) - searchWindow
+	if searchStart < 0 {
+		searchStart = 0
+	}
+	for i := len(s) - 1; i >= searchStart; i-- {
+		if s[i] == '\n' {
+			return i
+		}
+	}
+	return -1
+}
+
+// findLastSpace finds the last space character within the last N characters
+// Returns the position of the space or -1 if not found
+func findLastSpace(s string, searchWindow int) int {
+	searchStart := len(s) - searchWindow
+	if searchStart < 0 {
+		searchStart = 0
+	}
+	for i := len(s) - 1; i >= searchStart; i-- {
+		if s[i] == ' ' || s[i] == '\t' {
+			return i
+		}
+	}
+	return -1
+}
 
+func (c *DiscordChannel) sendChunk(ctx context.Context, channelID, content string) error {
 	// 使用传入的 ctx 进行超时控制
 	sendCtx, cancel := context.WithTimeout(ctx, sendTimeout)
 	defer cancel()
 
 	done := make(chan error, 1)
 	go func() {
-		_, err := c.session.ChannelMessageSend(channelID, message)
+		_, err := c.session.ChannelMessageSend(channelID, content)
 		done <- err
 	}()
 

pkg/tools/web.go

@@ -114,7 +114,7 @@ func (p *DuckDuckGoSearchProvider) Search(ctx context.Context, query string, cou
 func (p *DuckDuckGoSearchProvider) extractResults(html string, count int, query string) (string, error) {
 	// Simple regex based extraction for DDG HTML
 	// Strategy: Find all result containers or key anchors directly
-	
+
 	// Try finding the result links directly first, as they are the most critical
 	// Pattern: <a class="result__a" href="...">Title</a>
 	// The previous regex was a bit strict. Let's make it more flexible for attributes order/content
@@ -133,14 +133,14 @@ func (p *DuckDuckGoSearchProvider) extractResults(html string, count int, query
 	// But simple global search for snippets might mismatch order.
 	// Since we only have the raw HTML string, let's just extract snippets globally and assume order matches (risky but simple for regex)
 	// Or better: Let's assume the snippet follows the link in the HTML
-	
+
 	// A better regex approach: iterate through text and find matches in order
 	// But for now, let's grab all snippets too
 	reSnippet := regexp.MustCompile(`<a class="result__snippet[^"]*".*?>([\s\S]*?)</a>`)
 	snippetMatches := reSnippet.FindAllStringSubmatch(html, count+5)
 
 	maxItems := min(len(matches), count)
-	
+
 	for i := 0; i < maxItems; i++ {
 		urlStr := matches[i][1]
 		title := stripTags(matches[i][2])
@@ -157,7 +157,7 @@ func (p *DuckDuckGoSearchProvider) extractResults(html string, count int, query
 		}
 
 		lines = append(lines, fmt.Sprintf("%d. %s\n   %s", i+1, title, urlStr))
-		
+
 		// Attempt to attach snippet if available and index aligns
 		if i < len(snippetMatches) {
 			snippet := stripTags(snippetMatches[i][1])