feat: better handling of oversized mails, and add junk option

cmd/paraclub-ai-mailer/main.go

@@ -116,22 +116,64 @@ func processEmails(imapClient *imap.IMAPClient, fetcher *fetcher.Fetcher, aiProc
 	logger.WithField("contextCount", len(contextContent)).Debug("Successfully fetched context content")
 
 	// Process each email
-	var processedCount, errorCount int
+	var processedCount, errorCount, skippedCount int
 	for _, email := range emails {
+		emailBodySize := len(email.Body)
 		logger.WithFields(logrus.Fields{
 			"subject":       email.Subject,
 			"from":          email.From,
 			"messageId":     email.ID,
+			"bodySizeBytes": emailBodySize,
 		}).Info("Processing email")
 
-		// Generate AI response
-		response, err := aiProcessor.GenerateReply(email.Body, contextContent)
+		// Check email size limit
+		if cfg.Processing.MaxEmailSizeBytes > 0 && emailBodySize > cfg.Processing.MaxEmailSizeBytes {
+			logger.WithFields(logrus.Fields{
+				"subject":       email.Subject,
+				"from":          email.From,
+				"bodySizeBytes": emailBodySize,
+				"maxSizeBytes":  cfg.Processing.MaxEmailSizeBytes,
+			}).Warn("Email body exceeds size limit, skipping")
+			skippedCount++
+
+			// Mark as AI-processed to prevent reprocessing
+			if markErr := imapClient.MarkAsAIProcessed(email); markErr != nil {
+				logger.WithFields(logrus.Fields{
+					"subject": email.Subject,
+					"error":   markErr,
+				}).Error("Failed to mark oversized email as AI-processed")
+			}
+			continue
+		}
+
+		// Extract clean email content (remove MIME boundaries, headers, etc.)
+		cleanEmailContent := imap.ExtractMessageContent(email.Body)
+		cleanContentSize := len(cleanEmailContent)
+		logger.WithFields(logrus.Fields{
+			"subject":           email.Subject,
+			"rawSize":           emailBodySize,
+			"cleanSize":         cleanContentSize,
+			"sizeReduction":     emailBodySize - cleanContentSize,
+		}).Debug("Extracted clean email content")
+
+		// Generate AI response with clean content
+		response, err := aiProcessor.GenerateReply(cleanEmailContent, contextContent)
 		if err != nil {
 			logger.WithFields(logrus.Fields{
 				"subject": email.Subject,
 				"error":   err,
 			}).Error("Failed to generate reply")
 			errorCount++
+
+			// Mark as AI-processed even on failure to prevent infinite retry loop
+			if markErr := imapClient.MarkAsAIProcessed(email); markErr != nil {
+				logger.WithFields(logrus.Fields{
+					"subject": email.Subject,
+					"error":   markErr,
+				}).Error("Failed to mark failed email as AI-processed")
+			} else {
+				logger.WithField("subject", email.Subject).Info("Marked failed email as AI-processed to prevent reprocessing")
+			}
 			continue
 		}
 		logger.WithField("responseLength", len(response)).Debug("Generated AI response")
@@ -180,5 +222,6 @@ func processEmails(imapClient *imap.IMAPClient, fetcher *fetcher.Fetcher, aiProc
 		"totalEmails": len(emails),
 		"processed":   processedCount,
 		"errors":      errorCount,
+		"skipped":     skippedCount,
 	}).Info("Completed email processing cycle")
 }

config.yaml.example

@@ -23,6 +23,10 @@ context:
 polling:
   interval: "5m"  # Examples: "30s", "1m", "1h"
 
+processing:
+  max_email_size_bytes: 102400  # Maximum email body size in bytes (100KB), 0 = no limit
+  skip_junk_emails: false  # Skip emails marked as junk/spam (not yet implemented)
+
 logging:
   level: "info"  # Options: "debug", "info", "warn", "error"
   file_path: "paraclub-ai-mailer.log"

config/config.go

@@ -16,6 +16,7 @@ type Config struct {
 	Context    ContextConfig    `yaml:"context"`
 	Polling    PollingConfig    `yaml:"polling"`
 	Logging    LoggingConfig    `yaml:"logging"`
+	Processing ProcessingConfig `yaml:"processing"`
 }
 
 type IMAPConfig struct {
@@ -49,6 +50,11 @@ type LoggingConfig struct {
 	FilePath string `yaml:"file_path"`
 }
 
+type ProcessingConfig struct {
+	MaxEmailSizeBytes int  `yaml:"max_email_size_bytes"` // Maximum email body size in bytes (0 = no limit)
+	SkipJunkEmails    bool `yaml:"skip_junk_emails"`     // Skip emails marked as junk/spam
+}
+
 func readFileContent(path string) (string, error) {
 	content, err := os.ReadFile(path)
 	if err != nil {
@@ -119,6 +125,8 @@ func Load(path string) (*Config, error) {
 		"pollingInterval":     config.Polling.Interval,
 		"loggingLevel":        config.Logging.Level,
 		"loggingFilePath":     config.Logging.FilePath,
+		"maxEmailSizeBytes":   config.Processing.MaxEmailSizeBytes,
+		"skipJunkEmails":      config.Processing.SkipJunkEmails,
 	}).Debug("Configuration loaded successfully")
 
 	return &config, nil

internal/imap/imap.go

@@ -266,7 +266,7 @@ func (ic *IMAPClient) SaveDraft(email Email, response string) (err error) {
 		email.From,
 		email.Subject,
 		email.Date.Format("Mon, 02 Jan 2006 15:04:05 -0700"),
-		extractMessageContent(email.Body))
+		ExtractMessageContent(email.Body))
 
 	literal := &MessageLiteral{
 		content: []byte(draft),
@@ -287,9 +287,9 @@ func (ic *IMAPClient) SaveDraft(email Email, response string) (err error) {
 	return nil
 }
 
-// extractMessageContent attempts to extract just the message content
+// ExtractMessageContent attempts to extract just the message content
 // by removing email headers and MIME boundaries
-func extractMessageContent(body string) string {
+func ExtractMessageContent(body string) string {
 	logger.WithField("bodyLength", len(body)).Debug("Starting message content extraction")
 	logger.WithField("rawInputBody", body).Debug("extractMessageContent: Raw input body")
 	msg, err := mail.ReadMessage(strings.NewReader(body))