feat: expand DSML tool-call alias and fence handling

Add support for DSML wrapper aliases (<dsml|tool_calls>, <|tool_calls>,
<｜tool_calls>) alongside canonical XML. Normalize mixed DSML/canonical
tags instead of rejecting them. Add tilde fence (~~~) support, fix
nested fence and unclosed fence handling, support CDATA-protected fence
content, and skip prose mentions when scanning for real tool blocks.
Mirror all changes between Go and Node.js runtimes.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

internal/toolcall/fence_edge_test.go

@@ -0,0 +1,66 @@
+package toolcall
+
+import (
+	"strings"
+	"testing"
+)
+
+// 4 反引号嵌套 3 反引号
+func TestStripFencedCodeBlocks_NestedFourBackticks(t *testing.T) {
+	text := "Before\n\x60\x60\x60\x60markdown\nHere is \x60\x60\x60 nested \x60\x60\x60 example\n\x60\x60\x60\x60\nAfter"
+	got := stripFencedCodeBlocks(text)
+	if !strings.Contains(got, "Before") || !strings.Contains(got, "After") {
+		t.Fatalf("expected Before and After preserved, got %q", got)
+	}
+	if strings.Contains(got, "nested") {
+		t.Fatalf("expected nested content stripped, got %q", got)
+	}
+}
+
+// 波浪线围栏
+func TestStripFencedCodeBlocks_TildeFence(t *testing.T) {
+	text := "Before\n~~~python\ncode here\n~~~\nAfter"
+	got := stripFencedCodeBlocks(text)
+	if !strings.Contains(got, "Before") || !strings.Contains(got, "After") {
+		t.Fatalf("expected Before/After, got %q", got)
+	}
+	if strings.Contains(got, "code here") {
+		t.Fatalf("expected code stripped, got %q", got)
+	}
+}
+
+// 未闭合围栏 + 后面跟真正的工具调用：不应返回空字符串
+func TestStripFencedCodeBlocks_UnclosedFencePreservesToolCall(t *testing.T) {
+	text := "Example:\n\x60\x60\x60xml\n<tool_calls><invoke name=\"read_file\"><parameter name=\"path\">README.md</parameter></invoke></tool_calls>\n\n<tool_calls><invoke name=\"search\"><parameter name=\"q\">go</parameter></invoke></tool_calls>"
+	got := stripFencedCodeBlocks(text)
+	if got == "" {
+		t.Fatalf("unclosed fence should not truncate everything — real tool call after the fence is lost")
+	}
+}
+
+// CDATA 内的围栏不应被剥离
+func TestStripFencedCodeBlocks_FenceInsideCDATA(t *testing.T) {
+	text := "<tool_calls><invoke name=\"write\">\n<parameter name=\"content\"><![CDATA[\n\x60\x60\x60python\nprint('hello')\n\x60\x60\x60\n]]></parameter>\n</invoke></tool_calls>"
+	got := stripFencedCodeBlocks(text)
+	if !strings.Contains(got, "\x60\x60\x60python") {
+		t.Fatalf("fenced code inside CDATA should be preserved, got %q", got)
+	}
+}
+
+// 连续多个围栏
+func TestStripFencedCodeBlocks_MultipleFences(t *testing.T) {
+	text := "Before\n\x60\x60\x60\nfence1\n\x60\x60\x60\nMiddle\n\x60\x60\x60\nfence2\n\x60\x60\x60\nAfter"
+	got := stripFencedCodeBlocks(text)
+	if !strings.Contains(got, "Before") || !strings.Contains(got, "Middle") || !strings.Contains(got, "After") {
+		t.Fatalf("expected non-fenced content preserved, got %q", got)
+	}
+}
+
+// 围栏包含内嵌 ``` 行但没有独立成行
+func TestStripFencedCodeBlocks_InlineBackticksNotFence(t *testing.T) {
+	text := "Before\n\x60\x60\x60go\nfmt.Println(\x60\x60\x60hello\x60\x60\x60)\n\x60\x60\x60\nAfter"
+	got := stripFencedCodeBlocks(text)
+	if !strings.Contains(got, "Before") || !strings.Contains(got, "After") {
+		t.Fatalf("expected Before/After, got %q", got)
+	}
+}

internal/toolcall/toolcalls_dsml.go

@@ -6,13 +6,13 @@ func normalizeDSMLToolCallMarkup(text string) (string, bool) {
 	if text == "" {
 		return "", true
 	}
-	hasDSML, hasCanonical := toolMarkupStylesOutsideIgnored(text)
-	if hasDSML && hasCanonical {
-		return text, false
-	}
-	if !hasDSML {
+	hasAliasLikeMarkup, _ := toolMarkupStylesOutsideIgnored(text)
+	if !hasAliasLikeMarkup {
 		return text, true
 	}
+	// Always normalize DSML aliases to canonical form, even when canonical
+	// tags coexist. Models frequently mix DSML wrapper tags with canonical
+	// inner tags (e.g., <｜tool_calls><invoke name="...">).
 	return replaceDSMLToolMarkupOutsideIgnored(text), true
 }
 
@@ -26,6 +26,24 @@ var dsmlToolMarkupAliases = []struct {
 	{"</|dsml|invoke>", "</invoke>"},
 	{"<|dsml|parameter", "<parameter"},
 	{"</|dsml|parameter>", "</parameter>"},
+	{"<dsml|tool_calls", "<tool_calls"},
+	{"</dsml|tool_calls>", "</tool_calls>"},
+	{"<dsml|invoke", "<invoke"},
+	{"</dsml|invoke>", "</invoke>"},
+	{"<dsml|parameter", "<parameter"},
+	{"</dsml|parameter>", "</parameter>"},
+	{"<|tool_calls", "<tool_calls"},
+	{"</|tool_calls>", "</tool_calls>"},
+	{"<|invoke", "<invoke"},
+	{"</|invoke>", "</invoke>"},
+	{"<|parameter", "<parameter"},
+	{"</|parameter>", "</parameter>"},
+	{"<｜tool_calls", "<tool_calls"},
+	{"</｜tool_calls>", "</tool_calls>"},
+	{"<｜invoke", "<invoke"},
+	{"</｜invoke>", "</invoke>"},
+	{"<｜parameter", "<parameter"},
+	{"</｜parameter>", "</parameter>"},
 }
 
 var canonicalToolMarkupPrefixes = []string{

internal/toolcall/toolcalls_parse.go

@@ -93,7 +93,11 @@ func filterToolCallsDetailed(parsed []ParsedToolCall) ([]ParsedToolCall, []strin
 
 func looksLikeToolCallSyntax(text string) bool {
 	lower := strings.ToLower(text)
-	return strings.Contains(lower, "<|dsml|tool_calls") || strings.Contains(lower, "<tool_calls")
+	return strings.Contains(lower, "<|dsml|tool_calls") ||
+		strings.Contains(lower, "<dsml|tool_calls") ||
+		strings.Contains(lower, "<｜tool_calls") ||
+		strings.Contains(lower, "<|tool_calls") ||
+		strings.Contains(lower, "<tool_calls")
 }
 
 func stripFencedCodeBlocks(text string) string {
@@ -107,6 +111,9 @@ func stripFencedCodeBlocks(text string) string {
 	inFence := false
 	fenceMarker := ""
 	inCDATA := false
+	// Track builder length when a fence opens so we can preserve content
+	// collected before the unclosed fence.
+	beforeFenceLen := 0
 	for _, line := range lines {
 		if inCDATA || cdataStartsBeforeFence(line) {
 			b.WriteString(line)
@@ -118,6 +125,7 @@ func stripFencedCodeBlocks(text string) string {
 			if marker, ok := parseFenceOpen(trimmed); ok {
 				inFence = true
 				fenceMarker = marker
+				beforeFenceLen = b.Len()
 				continue
 			}
 			b.WriteString(line)
@@ -131,6 +139,12 @@ func stripFencedCodeBlocks(text string) string {
 	}
 
 	if inFence {
+		// Unclosed fence: preserve content that was collected before the
+		// fence started rather than dropping everything.
+		result := b.String()
+		if beforeFenceLen > 0 && beforeFenceLen <= len(result) {
+			return result[:beforeFenceLen]
+		}
 		return ""
 	}
 	return b.String()

internal/toolcall/toolcalls_parse_markup.go

@@ -124,7 +124,8 @@ func findXMLElementBlocks(text, tag string) []xmlElementBlock {
 		}
 		closeStart, closeEnd, ok := findMatchingXMLEndTagOutsideCDATA(text, tag, bodyStart)
 		if !ok {
-			break
+			pos = bodyStart
+			continue
 		}
 		out = append(out, xmlElementBlock{
 			Attrs: attrs,

internal/toolcall/toolcalls_test.go

@@ -53,11 +53,16 @@ func TestParseToolCallsSupportsDSMLShellWithCanonicalExampleInCDATA(t *testing.T
 	}
 }
 
-func TestParseToolCallsRejectsMixedDSMLAndCanonicalToolTags(t *testing.T) {
+func TestParseToolCallsNormalizesMixedDSMLAndCanonicalToolTags(t *testing.T) {
+	// Models commonly mix DSML wrapper tags with canonical inner tags.
+	// These should be normalized and parsed, not rejected.
 	text := `<|DSML|tool_calls><invoke name="Bash"><|DSML|parameter name="command">pwd</|DSML|parameter></invoke></|DSML|tool_calls>`
 	calls := ParseToolCalls(text, []string{"Bash"})
-	if len(calls) != 0 {
-		t.Fatalf("expected mixed DSML/XML tool tags to be rejected, got %#v", calls)
+	if len(calls) != 1 {
+		t.Fatalf("expected mixed DSML/XML tool tags to be normalized and parsed, got %#v", calls)
+	}
+	if calls[0].Name != "Bash" || calls[0].Input["command"] != "pwd" {
+		t.Fatalf("unexpected mixed DSML parse result: %#v", calls[0])
 	}
 }
 
@@ -438,3 +443,25 @@ func TestParseToolCallsParsesAfterFourBacktickFence(t *testing.T) {
 		t.Fatalf("expected non-fenced tool call to be parsed, got %#v", res.Calls[0])
 	}
 }
+
+func TestParseToolCallsSkipsProseMentionOfSameWrapperVariant(t *testing.T) {
+	text := strings.Join([]string{
+		"Summary: support canonical <tool_calls> and DSML <|DSML|tool_calls> wrappers.",
+		"",
+		"<|DSML|tool_calls>",
+		"<|DSML|invoke name=\"Bash\">",
+		"<|DSML|parameter name=\"command\"><![CDATA[git status]]></|DSML|parameter>",
+		"</|DSML|invoke>",
+		"</|DSML|tool_calls>",
+	}, "\n")
+	res := ParseToolCallsDetailed(text, []string{"Bash"})
+	if len(res.Calls) != 1 {
+		t.Fatalf("expected one parsed call after prose mention, got %#v", res.Calls)
+	}
+	if res.Calls[0].Name != "Bash" {
+		t.Fatalf("expected Bash call, got %#v", res.Calls[0])
+	}
+	if got, _ := res.Calls[0].Input["command"].(string); got != "git status" {
+		t.Fatalf("expected command to parse, got %q", got)
+	}
+}