internal/mail/imap.go

@@ -283,6 +283,39 @@ func (w *IMAPWatcher) fetchUnseen(c *imapclient.Client) error {
 	return nil
 }
 
+// resolveThreadID determines the thread_id for a message.
+// It tries In-Reply-To first, then falls back to References (last-to-first).
+// Returns the message's own ID if no parent is found.
+func resolveThreadID(messageID, inReplyTo, references string, lookup func(string) (*database.Task, error)) string {
+	if inReplyTo != "" {
+		if parent, err := lookup(inReplyTo); err == nil && parent != nil {
+			return parent.ThreadID
+		}
+	}
+
+	for _, refID := range parseReferences(references) {
+		if parent, err := lookup(refID); err == nil && parent != nil {
+			return parent.ThreadID
+		}
+	}
+
+	return messageID
+}
+
+// parseReferences splits a References header value into individual message IDs,
+// returned in reverse order (most recent first).
+func parseReferences(header string) []string {
+	if header == "" {
+		return nil
+	}
+	raw := strings.Fields(header)
+	// Reverse: last (most recent) first.
+	for i, j := 0, len(raw)-1; i < j; i, j = i+1, j-1 {
+		raw[i], raw[j] = raw[j], raw[i]
+	}
+	return raw
+}
+
 // processMessage handles a single fetched email message.
 func (w *IMAPWatcher) processMessage(c *imapclient.Client, buf *imapclient.FetchMessageBuffer, bodySection *imap.FetchItemBodySection) {
 	env := buf.Envelope
@@ -333,6 +366,7 @@ func (w *IMAPWatcher) processMessage(c *imapclient.Client, buf *imapclient.Fetch
 	// 4. Threading: determine thread_id.
 	threadID := messageID
 	inReplyTo := ""
+	references := ""
 
 	// Parse body to get In-Reply-To / References headers and plain text.
 	bodyPlain := ""
@@ -340,10 +374,12 @@ func (w *IMAPWatcher) processMessage(c *imapclient.Client, buf *imapclient.Fetch
 	if rawBody != nil {
 		mr, err := gomessage.CreateReader(io.NopCloser(strings.NewReader(string(rawBody))))
 		if err == nil {
-			// Extract In-Reply-To header.
 			if irt, err := mr.Header.Text("In-Reply-To"); err == nil && irt != "" {
 				inReplyTo = strings.TrimSpace(irt)
 			}
+			if refs, err := mr.Header.Text("References"); err == nil && refs != "" {
+				references = refs
+			}
 
 			// Read body parts for plain text.
 			for {
@@ -361,12 +397,9 @@ func (w *IMAPWatcher) processMessage(c *imapclient.Client, buf *imapclient.Fetch
 		}
 	}
 
-	if inReplyTo != "" {
-		parent, err := database.FindByMessageID(w.db, inReplyTo)
-		if err == nil && parent != nil {
-			threadID = parent.ThreadID
-		}
-	}
+	threadID = resolveThreadID(messageID, inReplyTo, references, func(mid string) (*database.Task, error) {
+		return database.FindByMessageID(w.db, mid)
+	})
 
 	// 5. Save task with status RECEIVED.
 	taskUUID := uuid.New().String()

internal/mail/resolve_thread_test.go

@@ -0,0 +1,86 @@
+package mail
+
+import (
+	"errors"
+	"testing"
+
+	"thuanle.me/claw-email-bridge/internal/database"
+)
+
+func TestResolveThreadID_NoHeaders_ReturnsMessageID(t *testing.T) {
+	got := resolveThreadID("msg-1", "", "", nilLookup)
+	if got != "msg-1" {
+		t.Fatalf("expected msg-1, got %s", got)
+	}
+}
+
+func TestResolveThreadID_InReplyToMatches_ReturnsParentThreadID(t *testing.T) {
+	lookup := func(messageID string) (*database.Task, error) {
+		if messageID == "<parent>" {
+			return &database.Task{ThreadID: "thread-abc"}, nil
+		}
+		return nil, nil
+	}
+	got := resolveThreadID("msg-2", "<parent>", "", lookup)
+	if got != "thread-abc" {
+		t.Fatalf("expected thread-abc, got %s", got)
+	}
+}
+
+func TestResolveThreadID_ReferencesOnly_LastIDMatches(t *testing.T) {
+	lookup := func(messageID string) (*database.Task, error) {
+		if messageID == "<C>" {
+			return &database.Task{ThreadID: "thread-c"}, nil
+		}
+		return nil, nil
+	}
+	got := resolveThreadID("msg-3", "", "<A> <B> <C>", lookup)
+	if got != "thread-c" {
+		t.Fatalf("expected thread-c, got %s", got)
+	}
+}
+
+func TestResolveThreadID_ReferencesOnly_MiddleIDMatches(t *testing.T) {
+	lookup := func(messageID string) (*database.Task, error) {
+		if messageID == "<B>" {
+			return &database.Task{ThreadID: "thread-b"}, nil
+		}
+		return nil, nil
+	}
+	got := resolveThreadID("msg-4", "", "<A> <B> <C>", lookup)
+	if got != "thread-b" {
+		t.Fatalf("expected thread-b, got %s", got)
+	}
+}
+
+func TestResolveThreadID_ReferencesOnly_NoMatch_ReturnsMessageID(t *testing.T) {
+	got := resolveThreadID("msg-5", "", "<X> <Y>", nilLookup)
+	if got != "msg-5" {
+		t.Fatalf("expected msg-5, got %s", got)
+	}
+}
+
+func TestResolveThreadID_InReplyToMiss_ReferencesMatches(t *testing.T) {
+	lookup := func(messageID string) (*database.Task, error) {
+		if messageID == "<ref>" {
+			return &database.Task{ThreadID: "thread-ref"}, nil
+		}
+		return nil, nil
+	}
+	got := resolveThreadID("msg-6", "<unknown>", "<ref>", lookup)
+	if got != "thread-ref" {
+		t.Fatalf("expected thread-ref, got %s", got)
+	}
+}
+
+func TestResolveThreadID_LookupError_ReturnsMessageID(t *testing.T) {
+	lookup := func(messageID string) (*database.Task, error) {
+		return nil, errors.New("db error")
+	}
+	got := resolveThreadID("msg-7", "<parent>", "", lookup)
+	if got != "msg-7" {
+		t.Fatalf("expected msg-7, got %s", got)
+	}
+}
+
+var nilLookup = func(string) (*database.Task, error) { return nil, nil }