feat: improve CDATA and DSML tag parsing robustness with support for fullwidth-bang, ideographic-comma, and extended quote/separator normalization.

internal/js/helpers/stream-tool-sieve/parse_payload.js

@@ -1,6 +1,6 @@
 'use strict';
 
-const CDATA_PATTERN = /^(?:<|〈)!\[CDATA\[([\s\S]*?)]](?:>|＞|〉)$/i;
+const CDATA_PATTERN = /^(?:<|〈)(?:!|！)\[CDATA\[([\s\S]*?)]](?:>|＞|〉)$/i;
 const XML_ATTR_PATTERN = /\b([a-z0-9_:-]+)\s*=\s*("([^"]*)"|'([^']*)')/gi;
 const TOOL_MARKUP_NAMES = [
   { raw: 'tool_calls', canonical: 'tool_calls' },
@@ -87,7 +87,8 @@ function isFenceCloseLine(trimmed, fenceChar, fenceLen) {
 }
 
 function cdataStartsBeforeFence(line) {
-  const cdataIdx = line.toLowerCase().indexOf('<![cdata[');
+  const cdataOpen = findNextCDATAOpen(line, 0);
+  const cdataIdx = cdataOpen.ok ? cdataOpen.start : -1;
   if (cdataIdx < 0) return false;
   const fenceIdx = Math.min(
     line.indexOf('```') >= 0 ? line.indexOf('```') : Infinity,
@@ -109,9 +110,9 @@ function updateCDATAStateLine(inCDATA, line) {
       state = false;
       continue;
     }
-    const start = lower.indexOf('<![cdata[', pos);
-    if (start < 0) return false;
-    pos = start + '<![cdata['.length;
+    const start = findNextCDATAOpen(line, pos);
+    if (!start.ok) return false;
+    pos = start.bodyStart;
     state = true;
   }
   return state;
@@ -410,8 +411,9 @@ function findMatchingXmlEndTagOutsideCDATA(text, tag, from) {
 }
 
 function skipXmlIgnoredSection(lower, i) {
-  if (lower.startsWith('<![cdata[', i)) {
-    const cdataEnd = findCDATAEnd(lower, i + '<![cdata['.length);
+  const cdataOpen = matchCDATAOpenAt(lower, i);
+  if (cdataOpen.ok) {
+    const cdataEnd = findCDATAEnd(lower, cdataOpen.bodyStart);
     const end = cdataEnd.index;
     if (end < 0) {
       return { advanced: false, blocked: true, next: i };
@@ -428,6 +430,50 @@ function skipXmlIgnoredSection(lower, i) {
   return { advanced: false, blocked: false, next: i };
 }
 
+function findNextCDATAOpen(text, from) {
+  const raw = toStringSafe(text);
+  for (let i = Math.max(0, from || 0); i < raw.length; i += 1) {
+    if (normalizeFullwidthASCIIChar(raw[i]) !== '<') {
+      continue;
+    }
+    const open = matchCDATAOpenAt(raw, i);
+    if (open.ok) {
+      return { ok: true, start: i, bodyStart: open.bodyStart };
+    }
+  }
+  return { ok: false, start: -1, bodyStart: -1 };
+}
+
+function matchCDATAOpenAt(text, start) {
+  const raw = toStringSafe(text);
+  if (start < 0 || start >= raw.length || normalizeFullwidthASCIIChar(raw[start]) !== '<') {
+    return { ok: false, bodyStart: start };
+  }
+  let i = start + 1;
+  for (let skipped = 0; skipped <= 4 && i < raw.length; skipped += 1) {
+    const matched = matchNormalizedASCII(raw, i, '[cdata[');
+    if (matched.ok) {
+      return { ok: true, bodyStart: i + matched.len };
+    }
+    if (!isCDATAOpenSeparator(raw[i])) {
+      break;
+    }
+    i += 1;
+  }
+  return { ok: false, bodyStart: start };
+}
+
+function isCDATAOpenSeparator(ch) {
+  const normalized = normalizeFullwidthASCIIChar(ch || '');
+  if (!normalized || ['<', '>', '/', '=', '"', "'", '['].includes(normalized)) {
+    return false;
+  }
+  if ([' ', '\t', '\n', '\r'].includes(normalized)) {
+    return false;
+  }
+  return !/^[A-Za-z0-9]$/.test(normalized);
+}
+
 function findCDATAEnd(text, from) {
   const ascii = text.indexOf(']]>', from);
   const fullwidth = text.indexOf(']]＞', from);
@@ -458,7 +504,7 @@ function scanToolMarkupTagAt(text, start) {
   while (i < raw.length && normalizeFullwidthASCIIChar(raw[i]) === '<') {
     i += 1;
   }
-  const closing = raw[i] === '/';
+  let closing = raw[i] === '/';
   if (closing) {
     i += 1;
   }
@@ -472,6 +518,9 @@ function scanToolMarkupTagAt(text, start) {
     if (!fallback.ok) {
       return null;
     }
+    if (!closing && toolMarkupPrefixContainsSlash(raw.slice(prefixStart, fallback.start))) {
+      closing = true;
+    }
     name = fallback.name;
     i = fallback.start;
     len = fallback.len;
@@ -692,6 +741,15 @@ function toolMarkupPrefixAllowsLocalName(prefix) {
   return !/^[A-Za-z0-9]$/.test(previous);
 }
 
+function toolMarkupPrefixContainsSlash(prefix) {
+  for (const ch of toStringSafe(prefix)) {
+    if (normalizeFullwidthASCIIChar(ch) === '/') {
+      return true;
+    }
+  }
+  return false;
+}
+
 function isToolMarkupTagTerminator(raw, idx) {
   return raw[idx] === '>' || normalizeFullwidthASCIIChar(raw[idx] || '') === '>';
 }
@@ -833,6 +891,12 @@ function normalizeFullwidthASCIIChar(ch) {
   if (ch === '〉') {
     return '>';
   }
+  if (ch === '“' || ch === '”') {
+    return '"';
+  }
+  if (ch === '‘' || ch === '’') {
+    return "'";
+  }
   const code = ch.charCodeAt(0);
   if (code >= 0xff01 && code <= 0xff5e) {
     return String.fromCharCode(code - 0xfee0);
@@ -882,7 +946,7 @@ function normalizeToolMarkupTagTailForXML(tail) {
     } else if (normalized === '"' || normalized === "'") {
       quote = normalized;
       out += normalized;
-    } else if (normalized === '|') {
+    } else if (normalized === '|' || normalized === '!') {
       let j = i + 1;
       while (j < raw.length && [' ', '\t', '\r', '\n'].includes(raw[j])) {
         j += 1;
@@ -1239,16 +1303,34 @@ function unescapeHtml(safe) {
 
 function extractStandaloneCDATA(inner) {
   const s = toStringSafe(inner).trim();
-  const cdataMatch = s.match(CDATA_PATTERN);
-  if (cdataMatch && cdataMatch[1] !== undefined) {
-    return { ok: true, value: cdataMatch[1] };
-  }
-  if (s.toLowerCase().startsWith('<![cdata[')) {
-    return { ok: true, value: s.slice('<![CDATA['.length) };
+  const open = matchCDATAOpenAt(s, 0);
+  if (open.ok) {
+    const close = findStandaloneCDATAEnd(s, open.bodyStart);
+    if (close.index < 0) {
+      return { ok: true, value: s.slice(open.bodyStart) };
+    }
+    return { ok: true, value: s.slice(open.bodyStart, close.index) };
   }
   return { ok: false, value: '' };
 }
 
+function findStandaloneCDATAEnd(text, from) {
+  const raw = toStringSafe(text);
+  let best = { index: -1, len: 0 };
+  for (let searchFrom = Math.max(0, from || 0); searchFrom < raw.length;) {
+    const close = findCDATAEnd(raw, searchFrom);
+    if (close.index < 0) {
+      break;
+    }
+    const closeEnd = close.index + close.len;
+    if (!raw.slice(closeEnd).trim()) {
+      best = close;
+    }
+    searchFrom = closeEnd;
+  }
+  return best;
+}
+
 function parseJSONLiteralValue(raw) {
   const s = toStringSafe(raw).trim();
   if (!s) {

internal/promptcompat/message_normalize.go

@@ -4,6 +4,7 @@ import (
 	"strings"
 
 	"ds2api/internal/prompt"
+	"ds2api/internal/toolcall"
 )
 
 const assistantReasoningLabel = "reasoning_content"
@@ -62,6 +63,9 @@ func buildAssistantContentForPrompt(msg map[string]any) string {
 		reasoning = strings.TrimSpace(extractOpenAIReasoningContentFromMessage(msg["content"]))
 	}
 	toolHistory := prompt.FormatToolCallsForPrompt(msg["tool_calls"])
+	if toolHistory == "" {
+		content = normalizeAssistantToolMarkupContentForPrompt(content)
+	}
 	parts := make([]string, 0, 3)
 	if reasoning != "" {
 		parts = append(parts, formatPromptLabeledBlock(assistantReasoningLabel, reasoning))
@@ -82,6 +86,40 @@ func buildAssistantContentForPrompt(msg map[string]any) string {
 	}
 }
 
+func normalizeAssistantToolMarkupContentForPrompt(content string) string {
+	trimmed := strings.TrimSpace(content)
+	if trimmed == "" || !isStandaloneAssistantToolMarkupBlock(trimmed) {
+		return content
+	}
+	parsed := toolcall.ParseStandaloneToolCallsDetailed(trimmed, nil)
+	if len(parsed.Calls) == 0 {
+		return content
+	}
+	raw := make([]any, 0, len(parsed.Calls))
+	for _, call := range parsed.Calls {
+		raw = append(raw, map[string]any{
+			"name":  call.Name,
+			"input": call.Input,
+		})
+	}
+	if formatted := prompt.FormatToolCallsForPrompt(raw); formatted != "" {
+		return formatted
+	}
+	return content
+}
+
+func isStandaloneAssistantToolMarkupBlock(trimmed string) bool {
+	tag, ok := toolcall.FindToolMarkupTagOutsideIgnored(trimmed, 0)
+	if !ok || tag.Start != 0 || tag.Closing || tag.Name != "tool_calls" {
+		return false
+	}
+	closeTag, ok := toolcall.FindMatchingToolMarkupClose(trimmed, tag)
+	if !ok {
+		return false
+	}
+	return strings.TrimSpace(trimmed[closeTag.End+1:]) == ""
+}
+
 func normalizeOpenAIReasoningContentForPrompt(v any) string {
 	switch x := v.(type) {
 	case string:

internal/promptcompat/message_normalize_test.go

@@ -263,6 +263,42 @@ func TestNormalizeOpenAIMessagesForPrompt_AssistantNilContentDoesNotInjectNullLi
 	}
 }
 
+func TestNormalizeOpenAIMessagesForPrompt_CanonicalizesStandaloneAssistantToolMarkupContent(t *testing.T) {
+	raw := []any{
+		map[string]any{
+			"role": "assistant",
+			"content": `<！DSML！tool_calls>
+  <！DSML！invoke name=“Bash”>
+  <！DSML！parameter name=“command”><！[CDATA[lsof -i :4321 -t]]><！/DSML！parameter>
+  <！DSML！parameter name=“description”><！[CDATA[Verify port 4321 is free]]><！/DSML！parameter>
+  <！/DSML！invoke>
+  <！/DSML！tool_calls>`,
+		},
+	}
+
+	normalized := NormalizeOpenAIMessagesForPrompt(raw, "")
+	if len(normalized) != 1 {
+		t.Fatalf("expected one normalized assistant message, got %#v", normalized)
+	}
+	content, _ := normalized[0]["content"].(string)
+	for _, want := range []string{
+		"<｜DSML｜tool_calls>",
+		`<｜DSML｜invoke name="Bash">`,
+		`<｜DSML｜parameter name="command"><![CDATA[lsof -i :4321 -t]]></｜DSML｜parameter>`,
+		`<｜DSML｜parameter name="description"><![CDATA[Verify port 4321 is free]]></｜DSML｜parameter>`,
+		"</｜DSML｜tool_calls>",
+	} {
+		if !strings.Contains(content, want) {
+			t.Fatalf("expected canonicalized assistant tool markup to contain %q, got %q", want, content)
+		}
+	}
+	for _, bad := range []string{"<！DSML", "！tool_calls", "“", "”"} {
+		if strings.Contains(content, bad) {
+			t.Fatalf("expected malformed assistant tool markup to be removed from prompt history, found %q in %q", bad, content)
+		}
+	}
+}
+
 func TestNormalizeOpenAIMessagesForPrompt_DeveloperRoleMapsToSystem(t *testing.T) {
 	raw := []any{
 		map[string]any{"role": "developer", "content": "必须先走工具调用"},

internal/toolcall/tool_prompt.go

@@ -21,6 +21,7 @@ RULES:
 1) Use the <｜DSML｜tool_calls> wrapper format.
 2) Put one or more <｜DSML｜invoke> entries under a single <｜DSML｜tool_calls> root.
 3) Put the tool name in the invoke name attribute: <｜DSML｜invoke name="TOOL_NAME">.
+3a) Tag punctuation alphabet: ASCII < > / = " plus the fullwidth vertical bar ｜.
 4) All string values must use <![CDATA[...]]>, even short ones. This includes code, scripts, file contents, prompts, paths, names, and queries.
 5) Every top-level argument must be a <｜DSML｜parameter name="ARG_NAME">...</｜DSML｜parameter> node.
 6) Objects use nested XML elements inside the parameter body. Arrays may repeat <item> children.

internal/toolcall/tool_prompt_test.go

@@ -133,6 +133,19 @@ func TestBuildToolCallInstructions_RejectsEmptyParametersInPrompt(t *testing.T)
 	}
 }
 
+func TestBuildToolCallInstructions_UsesPositiveTagPunctuationAlphabet(t *testing.T) {
+	out := BuildToolCallInstructions([]string{"Bash"})
+	want := `Tag punctuation alphabet: ASCII < > / = " plus the fullwidth vertical bar ｜.`
+	if !strings.Contains(out, want) {
+		t.Fatalf("expected positive tag punctuation alphabet %q, got: %s", want, out)
+	}
+	for _, bad := range []string{"lookalike", "substitute", "！", "〈", "〉", "“", "”", "、"} {
+		if strings.Contains(out, bad) {
+			t.Fatalf("tool prompt should not include negative punctuation examples %q, got: %s", bad, out)
+		}
+	}
+}
+
 func findInvokeBlocks(text, name string) []string {
 	open := `<｜DSML｜invoke name="` + name + `">`
 	remaining := text

internal/toolcall/toolcalls_dsml.go

@@ -86,7 +86,7 @@ func normalizeToolMarkupTagTailForXML(tail string) string {
 		case '"', '\'':
 			quote = ch
 			b.WriteRune(ch)
-		case '|':
+		case '|', '!':
 			j := i + size
 			for j < len(tail) {
 				next, nextSize := utf8.DecodeRuneInString(tail[j:])

internal/toolcall/toolcalls_markup.go

@@ -10,7 +10,7 @@ import (
 var toolCallMarkupKVPattern = regexp.MustCompile(`(?is)<(?:[a-z0-9_:-]+:)?([a-z0-9_\-.]+)\b[^>]*>(.*?)</(?:[a-z0-9_:-]+:)?([a-z0-9_\-.]+)>`)
 
 // cdataPattern matches a standalone CDATA section.
-var cdataPattern = regexp.MustCompile(`(?is)^(?:<|〈)!\[CDATA\[(.*?)]](?:>|＞|〉)$`)
+var cdataPattern = regexp.MustCompile(`(?is)^(?:<|〈)(?:!|！)\[CDATA\[(.*?)]](?:>|＞|〉)$`)
 
 func parseMarkupKVObject(text string) map[string]any {
 	matches := toolCallMarkupKVPattern.FindAllStringSubmatch(strings.TrimSpace(text), -1)
@@ -108,15 +108,32 @@ func extractRawTagValue(inner string) string {
 
 func extractStandaloneCDATA(inner string) (string, bool) {
 	trimmed := strings.TrimSpace(inner)
-	if cdataMatches := cdataPattern.FindStringSubmatch(trimmed); len(cdataMatches) >= 2 {
-		return cdataMatches[1], true
-	}
-	if strings.HasPrefix(strings.ToLower(trimmed), "<![cdata[") {
-		return trimmed[len("<![CDATA["):], true
+	if bodyStart, ok := matchToolCDATAOpenAt(trimmed, 0); ok {
+		end := findStandaloneCDATAEnd(trimmed, bodyStart)
+		if end < 0 {
+			return trimmed[bodyStart:], true
+		}
+		return trimmed[bodyStart:end], true
 	}
 	return "", false
 }
 
+func findStandaloneCDATAEnd(text string, from int) int {
+	end := -1
+	for searchFrom := from; searchFrom < len(text); {
+		next := indexToolCDATAClose(text, searchFrom)
+		if next < 0 {
+			break
+		}
+		closeEnd := next + toolCDATACloseLenAt(text, next)
+		if strings.TrimSpace(text[closeEnd:]) == "" {
+			end = next
+		}
+		searchFrom = closeEnd
+	}
+	return end
+}
+
 func parseJSONLiteralValue(raw string) (any, bool) {
 	trimmed := strings.TrimSpace(raw)
 	if trimmed == "" {

internal/toolcall/toolcalls_parse_markup.go

@@ -209,13 +209,14 @@ func skipXMLIgnoredSection(text string, i int) (next int, advanced bool, blocked
 	if i < 0 || i >= len(text) {
 		return i, false, false
 	}
-	switch {
-	case hasASCIIPrefixFoldAt(text, i, "<![cdata["):
-		end := findToolCDATAEnd(text, i+len("<![cdata["))
+	if bodyStart, ok := matchToolCDATAOpenAt(text, i); ok {
+		end := findToolCDATAEnd(text, bodyStart)
 		if end < 0 {
 			return 0, false, true
 		}
 		return end + toolCDATACloseLenAt(text, end), true, false
+	}
+	switch {
 	case strings.HasPrefix(text[i:], "<!--"):
 		end := strings.Index(text[i+len("<!--"):], "-->")
 		if end < 0 {
@@ -227,6 +228,38 @@ func skipXMLIgnoredSection(text string, i int) (next int, advanced bool, blocked
 	}
 }
 
+func matchToolCDATAOpenAt(text string, start int) (int, bool) {
+	i, ok := consumeToolMarkupLessThan(text, start)
+	if !ok {
+		return start, false
+	}
+	for skipped := 0; skipped <= 4 && i < len(text); skipped++ {
+		if cdataLen, ok := matchASCIIPrefixFoldAt(text, i, "[cdata["); ok {
+			return i + cdataLen, true
+		}
+		r, size := utf8.DecodeRuneInString(text[i:])
+		if size <= 0 || !isToolCDATAOpenSeparator(r) {
+			break
+		}
+		i += size
+	}
+	return start, false
+}
+
+func isToolCDATAOpenSeparator(r rune) bool {
+	ch := normalizeFullwidthASCII(r)
+	if ch == 0 || ch == '<' || ch == '>' || ch == '/' || ch == '=' || ch == '"' || ch == '\'' || ch == '[' {
+		return false
+	}
+	if ch == ' ' || ch == '\t' || ch == '\n' || ch == '\r' {
+		return false
+	}
+	if (ch >= 'a' && ch <= 'z') || (ch >= 'A' && ch <= 'Z') || (ch >= '0' && ch <= '9') {
+		return false
+	}
+	return true
+}
+
 func hasASCIIPrefixFoldAt(text string, start int, prefix string) bool {
 	_, ok := matchASCIIPrefixFoldAt(text, start, prefix)
 	return ok

internal/toolcall/toolcalls_scan.go

@@ -159,6 +159,9 @@ func scanToolMarkupTagAt(text string, start int) (ToolMarkupTag, bool) {
 		if !ok {
 			return ToolMarkupTag{}, false
 		}
+		if !closing && toolMarkupPrefixContainsSlash(text[prefixStart:fallbackStart]) {
+			closing = true
+		}
 		name = fallbackName
 		i = fallbackStart
 		nameLen = fallbackLen
@@ -461,6 +464,9 @@ func consumeToolMarkupPipe(text string, idx int) (int, bool) {
 	if strings.HasPrefix(text[idx:], "␂") {
 		return idx + len("␂"), true
 	}
+	if ch, size := normalizedASCIIAt(text, idx); ch == '!' {
+		return idx + size, true
+	}
 	return idx, false
 }
 
@@ -506,9 +512,22 @@ func normalizeFullwidthASCII(r rune) rune {
 		return '<'
 	case '〉':
 		return '>'
+	case '“', '”':
+		return '"'
+	case '‘', '’':
+		return '\''
 	}
 	if r >= '！' && r <= '～' {
 		return r - 0xFEE0
 	}
 	return r
 }
+
+func toolMarkupPrefixContainsSlash(prefix string) bool {
+	for _, r := range prefix {
+		if normalizeFullwidthASCII(r) == '/' {
+			return true
+		}
+	}
+	return false
+}

internal/toolcall/toolcalls_test.go

@@ -163,6 +163,49 @@ func TestParseToolCallsSupportsCJKAngleDSMDrift(t *testing.T) {
 	}
 }
 
+func TestParseToolCallsSupportsFullwidthBangDSMLDrift(t *testing.T) {
+	text := `<！DSML！tool_calls>
+  <！DSML！invoke name=“Bash”>
+  <！DSML！parameter name=“command”><！[CDATA[lsof -i :4321 -t]]><！/DSML！parameter>
+  <！DSML！parameter name=“description”><！[CDATA[Verify port 4321 is free]]><！/DSML！parameter>
+  <！/DSML！invoke>
+  <！/DSML！tool_calls>`
+
+	calls := ParseToolCalls(text, []string{"Bash"})
+	if len(calls) != 1 {
+		t.Fatalf("expected one fullwidth-bang DSML drift call, got %#v", calls)
+	}
+	if calls[0].Name != "Bash" || calls[0].Input["command"] != "lsof -i :4321 -t" || calls[0].Input["description"] != "Verify port 4321 is free" {
+		t.Fatalf("unexpected fullwidth-bang DSML drift call: %#v", calls[0])
+	}
+}
+
+func TestParseToolCallsSupportsIdeographicCommaDSMLDrift(t *testing.T) {
+	text := `<、DSML、tool_calls>
+  <、DSML、invoke name="Bash">
+    <、DSML、parameter name="command"><、[CDATA[git commit -m "$(cat <<'EOF'
+feat: expand fullwidth bang separator and curly quote tolerance in DSML tool parsing
+
+Co-Authored-By: Claude Opus 4.6 noreply@anthropic.com
+EOF
+)"]]><、/DSML、parameter>
+    <、DSML、parameter name="description"><、[CDATA[Create commit with staged changes]]><、/DSML、parameter>
+  <、/DSML、invoke>
+<、/DSML、tool_calls>`
+
+	calls := ParseToolCalls(text, []string{"Bash"})
+	if len(calls) != 1 {
+		t.Fatalf("expected one ideographic-comma DSML drift call, got %#v", calls)
+	}
+	command, _ := calls[0].Input["command"].(string)
+	if calls[0].Name != "Bash" || !strings.Contains(command, `git commit -m "$(cat <<'EOF'`) || !strings.Contains(command, "Co-Authored-By: Claude Opus 4.6 noreply@anthropic.com") {
+		t.Fatalf("unexpected ideographic-comma DSML drift call: %#v", calls[0])
+	}
+	if calls[0].Input["description"] != "Create commit with staged changes" {
+		t.Fatalf("unexpected ideographic-comma description: %#v", calls[0])
+	}
+}
+
 func TestParseToolCallsIgnoresBareHyphenatedToolCallsLookalike(t *testing.T) {
 	text := `<tool-calls><invoke name="Bash"><parameter name="command">pwd</parameter></invoke></tool-calls>`
 	calls := ParseToolCalls(text, []string{"Bash"})

internal/toolstream/tool_sieve_xml_test.go

@@ -1262,3 +1262,76 @@ func TestProcessToolSieveCJKAngleDSMDriftDoesNotLeak(t *testing.T) {
 		t.Fatalf("unexpected CJK-angle DSM drift call: %#v", calls[0])
 	}
 }
+
+func TestProcessToolSieveFullwidthBangDSMLDriftDoesNotLeak(t *testing.T) {
+	var state State
+	chunks := []string{
+		"<！DSML！tool_calls>\n",
+		"  <！DSML！invoke name=“Bash”>\n",
+		"  <！DSML！parameter name=“command”><！[CDATA[lsof -i :4321 -t]]><！/DSML！parameter>\n",
+		"  <！DSML！parameter name=“description”><！[CDATA[Verify port 4321 is free]]><！/DSML！parameter>\n",
+		"  <！/DSML！invoke>\n",
+		"  <！/DSML！tool_calls>",
+	}
+	var events []Event
+	for _, c := range chunks {
+		events = append(events, ProcessChunk(&state, c, []string{"Bash"})...)
+	}
+	events = append(events, Flush(&state, []string{"Bash"})...)
+
+	var textContent string
+	var calls []toolcall.ParsedToolCall
+	for _, evt := range events {
+		textContent += evt.Content
+		calls = append(calls, evt.ToolCalls...)
+	}
+
+	if strings.Contains(textContent, "DSML") || strings.Contains(textContent, "lsof") {
+		t.Fatalf("fullwidth-bang DSML drift leaked to text: %q events=%#v", textContent, events)
+	}
+	if len(calls) != 1 {
+		t.Fatalf("expected one fullwidth-bang DSML drift tool call, got %d events=%#v", len(calls), events)
+	}
+	if calls[0].Name != "Bash" || calls[0].Input["command"] != "lsof -i :4321 -t" {
+		t.Fatalf("unexpected fullwidth-bang DSML drift call: %#v", calls[0])
+	}
+}
+
+func TestProcessToolSieveIdeographicCommaDSMLDriftDoesNotLeak(t *testing.T) {
+	var state State
+	chunks := []string{
+		"<、DSML、tool_calls>\n",
+		"  <、DSML、invoke name=\"Bash\">\n",
+		"    <、DSML、parameter name=\"command\"><、[CDATA[git commit -m \"$(cat <<'EOF'\n",
+		"feat: expand fullwidth bang separator and curly quote tolerance in DSML tool parsing\n\n",
+		"Co-Authored-By: Claude Opus 4.6 noreply@anthropic.com\n",
+		"EOF\n",
+		")\"]]><、/DSML、parameter>\n",
+		"    <、DSML、parameter name=\"description\"><、[CDATA[Create commit with staged changes]]><、/DSML、parameter>\n",
+		"  <、/DSML、invoke>\n",
+		"<、/DSML、tool_calls>",
+	}
+	var events []Event
+	for _, c := range chunks {
+		events = append(events, ProcessChunk(&state, c, []string{"Bash"})...)
+	}
+	events = append(events, Flush(&state, []string{"Bash"})...)
+
+	var textContent string
+	var calls []toolcall.ParsedToolCall
+	for _, evt := range events {
+		textContent += evt.Content
+		calls = append(calls, evt.ToolCalls...)
+	}
+
+	if strings.Contains(textContent, "DSML") || strings.Contains(textContent, "git commit") {
+		t.Fatalf("ideographic-comma DSML drift leaked to text: %q events=%#v", textContent, events)
+	}
+	if len(calls) != 1 {
+		t.Fatalf("expected one ideographic-comma DSML drift tool call, got %d events=%#v", len(calls), events)
+	}
+	command, _ := calls[0].Input["command"].(string)
+	if calls[0].Name != "Bash" || !strings.Contains(command, "git commit -m") {
+		t.Fatalf("unexpected ideographic-comma DSML drift call: %#v", calls[0])
+	}
+}