From 4ffe555bfda9712b6342fd5fbaa7a5c9ca794057 Mon Sep 17 00:00:00 2001
From: Lukasz Raczylo <lukasz@raczylo.com>
Date: Sun, 7 Jun 2026 14:34:35 +0100
Subject: [PATCH] fix(captcha): strip reasoning-model <think> blocks before
 json extraction

Reasoning models prefix responses with <think>...</think> (or
<thinking>...</thinking>) scratchpad that can itself contain a JSON-looking
object. The brace-counting extractor would grab that inner object instead of
the real answer. Strip think/thinking blocks via a package-level regexp before
the balanced-object scan. Adds table cases covering both tag spellings while
keeping the plain, prose-wrapped, and unbalanced cases intact.
---
 internal/captcha/json.go      | 13 ++++++++++++-
 internal/captcha/json_test.go | 10 ++++++++++
 2 files changed, 22 insertions(+), 1 deletion(-)

diff --git a/internal/captcha/json.go b/internal/captcha/json.go
index 274b2c6..6b1f532 100644
--- a/internal/captcha/json.go
+++ b/internal/captcha/json.go
@@ -1,13 +1,24 @@
 package captcha
 
-import "strings"
+import (
+	"regexp"
+	"strings"
+)
+
+// thinkRe matches reasoning-model scratchpad blocks (<think>…</think> or
+// <thinking>…</thinking>). These can themselves contain JSON-looking objects,
+// so they are stripped before the brace scan to avoid grabbing the wrong object.
+var thinkRe = regexp.MustCompile(`(?s)<think(?:ing)?>.*?</think(?:ing)?>`)
 
 // extractJSON returns the first balanced {...} object found in s, or s unchanged
 // if no opening brace is present. It scans by brace depth so prose, markdown
 // fences, or an example object before the real one do not corrupt parsing.
+// Reasoning-model <think>…</think> blocks are stripped first so a JSON-looking
+// object inside the scratchpad is not mistaken for the answer.
 // Note: it does not account for braces inside string literals; that is
 // acceptable for the short, structured captcha responses this handles.
 func extractJSON(s string) string {
+	s = thinkRe.ReplaceAllString(s, "")
 	start := strings.IndexByte(s, '{')
 	if start < 0 {
 		return s
diff --git a/internal/captcha/json_test.go b/internal/captcha/json_test.go
index 564151b..27e703e 100644
--- a/internal/captcha/json_test.go
+++ b/internal/captcha/json_test.go
@@ -27,6 +27,16 @@ func TestExtractJSON(t *testing.T) {
 		},
 		{"no brace", `no json here`, `no json here`},
 		{"unbalanced returns from start", `tail {"text":"x"`, `{"text":"x"`},
+		{
+			"think block stripped, real object wins",
+			"<think>reasoning with {\"tiles\":[9]}</think>\n{\"tiles\":[0,1,2],\"confidence\":0.9}",
+			`{"tiles":[0,1,2],"confidence":0.9}`,
+		},
+		{
+			"thinking block stripped",
+			`<thinking>let me reason {"tiles":[5]}</thinking>{"text":"ab12"}`,
+			`{"text":"ab12"}`,
+		},
 	}
 	for _, tc := range tests {
 		t.Run(tc.name, func(t *testing.T) {