From 0a23c77ff73b56c7fd196ee6afa69b131df492a1 Mon Sep 17 00:00:00 2001
From: CJACK <tetr20071102@gmail.com>
Date: Sun, 12 Apr 2026 17:43:57 +0800
Subject: [PATCH] feat: add sanitization for think tags and BOS markers in
 leaked output and update golang.org/x/net dependency

---
 go.mod                                                |  2 +-
 internal/adapter/openai/leaked_output_sanitize.go     | 11 ++++++++++-
 .../adapter/openai/leaked_output_sanitize_test.go     |  8 ++++++++
 3 files changed, 19 insertions(+), 2 deletions(-)

diff --git a/go.mod b/go.mod
index 1471913..2613f89 100644
--- a/go.mod
+++ b/go.mod
@@ -18,7 +18,7 @@ require (
 	github.com/tidwall/pretty v1.2.1 // indirect
 	github.com/tidwall/sjson v1.2.5 // indirect
 	golang.org/x/crypto v0.49.0 // indirect
-	golang.org/x/net v0.52.0 // indirect
+	golang.org/x/net v0.52.0
 	golang.org/x/sys v0.42.0 // indirect
 	gopkg.in/yaml.v3 v3.0.1 // indirect
 )
diff --git a/internal/adapter/openai/leaked_output_sanitize.go b/internal/adapter/openai/leaked_output_sanitize.go
index c139feb..bcd8227 100644
--- a/internal/adapter/openai/leaked_output_sanitize.go
+++ b/internal/adapter/openai/leaked_output_sanitize.go
@@ -8,7 +8,14 @@ var emptyJSONFencePattern = regexp.MustCompile("(?is)```json\\s*```")
 var leakedToolCallArrayPattern = regexp.MustCompile(`(?is)\[\{\s*"function"\s*:\s*\{[\s\S]*?\}\s*,\s*"id"\s*:\s*"call[^"]*"\s*,\s*"type"\s*:\s*"function"\s*}\]`)
 var leakedToolResultBlobPattern = regexp.MustCompile(`(?is)<\s*\|\s*tool\s*\|\s*>\s*\{[\s\S]*?"tool_call_id"\s*:\s*"call[^"]*"\s*}`)
 
-// leakedMetaMarkerPattern matches DeepSeek special tokens in BOTH forms:
+var leakedThinkTagPattern = regexp.MustCompile(`(?i)</?think>`)
+
+// leakedBOSMarkerPattern matches DeepSeek BOS markers in BOTH forms:
+//   - ASCII underscore: <｜begin_of_sentence｜>
+//   - U+2581 variant:   <｜begin▁of▁sentence｜>
+var leakedBOSMarkerPattern = regexp.MustCompile(`(?i)<[｜\|]\s*begin[_▁]of[_▁]sentence\s*[｜\|]>`)
+
+// leakedMetaMarkerPattern matches the remaining DeepSeek special tokens in BOTH forms:
 //   - ASCII underscore: <｜end_of_sentence｜>, <｜end_of_toolresults｜>, <｜end_of_instructions｜>
 //   - U+2581 variant:   <｜end▁of▁sentence｜>, <｜end▁of▁toolresults｜>, <｜end▁of▁instructions｜>
 var leakedMetaMarkerPattern = regexp.MustCompile(`(?i)<[｜\|]\s*(?:assistant|tool|end[_▁]of[_▁]sentence|end[_▁]of[_▁]thinking|end[_▁]of[_▁]toolresults|end[_▁]of[_▁]instructions)\s*[｜\|]>`)
@@ -35,6 +42,8 @@ func sanitizeLeakedOutput(text string) string {
 	out := emptyJSONFencePattern.ReplaceAllString(text, "")
 	out = leakedToolCallArrayPattern.ReplaceAllString(out, "")
 	out = leakedToolResultBlobPattern.ReplaceAllString(out, "")
+	out = leakedThinkTagPattern.ReplaceAllString(out, "")
+	out = leakedBOSMarkerPattern.ReplaceAllString(out, "")
 	out = leakedMetaMarkerPattern.ReplaceAllString(out, "")
 	out = sanitizeLeakedAgentXMLBlocks(out)
 	return out
diff --git a/internal/adapter/openai/leaked_output_sanitize_test.go b/internal/adapter/openai/leaked_output_sanitize_test.go
index 558cc48..6fd1485 100644
--- a/internal/adapter/openai/leaked_output_sanitize_test.go
+++ b/internal/adapter/openai/leaked_output_sanitize_test.go
@@ -26,6 +26,14 @@ func TestSanitizeLeakedOutputRemovesStandaloneMetaMarkers(t *testing.T) {
 	}
 }
 
+func TestSanitizeLeakedOutputRemovesThinkAndBosMarkers(t *testing.T) {
+	raw := "A<think>B</think>C<｜begin▁of▁sentence｜>D<| begin_of_sentence |>E<｜begin_of_sentence｜>F"
+	got := sanitizeLeakedOutput(raw)
+	if got != "ABCDEF" {
+		t.Fatalf("unexpected sanitize result for think/BOS markers: %q", got)
+	}
+}
+
 func TestSanitizeLeakedOutputRemovesAgentXMLLeaks(t *testing.T) {
 	raw := "Done.<attempt_completion><result>Some final answer</result></attempt_completion>"
 	got := sanitizeLeakedOutput(raw)