diff --git a/amethyst/src/main/java/com/vitorpamplona/amethyst/ui/components/LatexEquation.kt b/amethyst/src/main/java/com/vitorpamplona/amethyst/ui/components/LatexEquation.kt
index 06e74738ec..2042fb82a1 100644
--- a/amethyst/src/main/java/com/vitorpamplona/amethyst/ui/components/LatexEquation.kt
+++ b/amethyst/src/main/java/com/vitorpamplona/amethyst/ui/components/LatexEquation.kt
@@ -53,6 +53,7 @@ import ru.noties.jlatexmath.JLatexMathDrawable
 fun LatexEquation(
     latex: String,
     displayMode: Boolean,
+    leading: String = "",
     trailing: String = "",
 ) {
     val color = LocalContentColor.current.toArgb()
@@ -86,7 +87,7 @@ fun LatexEquation(
 
     if (drawable == null) {
         // Couldn't parse — show the raw delimited source so nothing is lost.
-        Text((if (displayMode) "$$$latex$$" else "$$latex$") + trailing)
+        Text(leading + (if (displayMode) "$$$latex$$" else "$$latex$") + trailing)
         return
     }
 
@@ -98,9 +99,12 @@ fun LatexEquation(
     val equationSize = Modifier.size(widthDp, heightDp)
     val equationModifier = if (displayMode) Modifier.horizontalScroll(rememberScrollState()).then(equationSize) else equationSize
 
-    // Row keeps trailing punctuation (the `.` in `$x$.`) hugging the equation
-    // rather than getting a word-gap from the parent FlowRow.
+    // Row keeps leading/trailing punctuation (the `(` and `)` in `($x$)`) hugging
+    // the equation rather than getting a word-gap from the parent FlowRow.
     Row(verticalAlignment = Alignment.CenterVertically) {
+        if (leading.isNotEmpty()) {
+            Text(leading)
+        }
         Canvas(modifier = equationModifier) {
             drawIntoCanvas { canvas ->
                 drawable.setBounds(0, 0, drawable.intrinsicWidth, drawable.intrinsicHeight)
diff --git a/amethyst/src/main/java/com/vitorpamplona/amethyst/ui/components/RichTextViewer.kt b/amethyst/src/main/java/com/vitorpamplona/amethyst/ui/components/RichTextViewer.kt
index 7192c486a2..37319f0b51 100644
--- a/amethyst/src/main/java/com/vitorpamplona/amethyst/ui/components/RichTextViewer.kt
+++ b/amethyst/src/main/java/com/vitorpamplona/amethyst/ui/components/RichTextViewer.kt
@@ -510,7 +510,7 @@ private fun RenderWordWithoutPreview(
 
         is SecretEmoji -> Text(word.segmentText)
 
-        is MathSegment -> LatexEquation(word.latex, word.displayMode, word.trailing)
+        is MathSegment -> LatexEquation(word.latex, word.displayMode, word.leading, word.trailing)
 
         is PhoneSegment -> ClickablePhone(word.segmentText)
 
@@ -554,7 +554,7 @@ private fun RenderWordWithPreview(
         is CashuSegment -> CashuPreview(word.segmentText, accountViewModel)
         is EmailSegment -> ClickableEmail(word.segmentText)
         is SecretEmoji -> DisplaySecretEmoji(word, state, callbackUri, true, quotesLeft, backgroundColor, accountViewModel, nav)
-        is MathSegment -> LatexEquation(word.latex, word.displayMode, word.trailing)
+        is MathSegment -> LatexEquation(word.latex, word.displayMode, word.leading, word.trailing)
         is PhoneSegment -> ClickablePhone(word.segmentText)
         is BechSegment -> BechLink(word.segmentText, true, quotesLeft, backgroundColor, accountViewModel, nav)
         is HashTagSegment -> HashTag(word, nav)
diff --git a/commons/src/commonMain/kotlin/com/vitorpamplona/amethyst/commons/richtext/MathParser.kt b/commons/src/commonMain/kotlin/com/vitorpamplona/amethyst/commons/richtext/MathParser.kt
index 5dbd6b8744..25d5af671a 100644
--- a/commons/src/commonMain/kotlin/com/vitorpamplona/amethyst/commons/richtext/MathParser.kt
+++ b/commons/src/commonMain/kotlin/com/vitorpamplona/amethyst/commons/richtext/MathParser.kt
@@ -39,8 +39,10 @@ package com.vitorpamplona.amethyst.commons.richtext
  *  - A `$` escaped with a backslash (`\$`) is a literal dollar, never a delimiter.
  *  - `$$...$$` (display) is matched before `$...$` (inline).
  *
- * Math glued to text without a separating space (e.g. `a$x$b`) stays a single
- * plain word and renders literally — only whitespace-delimited spans become math.
+ * Math glued to alphanumeric text without a separating space (e.g. `a$x$b`)
+ * stays a single plain word and renders literally. A span glued only to leading
+ * opening punctuation — a paren, bracket, or quote, as in `($x$)` — is still
+ * detected: the punctuation rides along as the equation's leading/trailing extras.
  */
 object MathParser {
     sealed interface Token {
@@ -51,14 +53,17 @@ object MathParser {
 
         /**
          * A math span. [raw] includes the `$` delimiters; [latex] is the inner
-         * formula. [trailing] holds any punctuation glued right after the closing
-         * `$` (e.g. the `.` in `$x$.`) so it renders next to the equation instead
-         * of drifting off behind a space — same idea as [HashTagSegment]'s extras.
+         * formula. [leading] holds any opening punctuation glued right before the
+         * opening `$` (e.g. the `(` in `($x$)`) and [trailing] any punctuation
+         * glued right after the closing `$` (e.g. the `.` in `$x$.`), so both
+         * render next to the equation instead of drifting off behind a space —
+         * same idea as [HashTagSegment]'s extras.
          */
         data class Math(
             val raw: String,
             val latex: String,
             val displayMode: Boolean,
+            val leading: String = "",
             val trailing: String = "",
         ) : Token
     }
@@ -87,13 +92,46 @@ object MathParser {
      * Splits [line] on spaces into [Token.Word]s, with any whitespace-delimited
      * math span surfaced as a [Token.Math].
      */
-    fun split(line: String): List<Token> =
-        splitKeepingMathWhole(line).map { cell ->
-            // A span at the start of the cell becomes math, carrying any trailing
-            // punctuation (`$x$.`). Leading-glued math (`a$x$`) stays a plain word.
-            val math = matchMathAt(cell, 0)
-            if (math != null) math.copy(trailing = cell.substring(math.raw.length)) else Token.Word(cell)
-        }
+    fun split(line: String): List<Token> = splitKeepingMathWhole(line).map(::toToken)
+
+    /**
+     * Turns one space-delimited [cell] into a token. A `$…$` span at the start of
+     * the cell — or behind a run of opening punctuation (`(`, `[`, `"`, …) —
+     * becomes math, with that punctuation kept as [Token.Math.leading] and any
+     * remainder (e.g. a closing `)` or `.`) as [Token.Math.trailing]. Anything
+     * else, including alphanumeric-glued math (`a$x$`), stays a plain word.
+     */
+    private fun toToken(cell: String): Token {
+        val dollar = mathStartIn(cell) ?: return Token.Word(cell)
+        val math = matchMathAt(cell, dollar) ?: return Token.Word(cell)
+        return math.copy(
+            leading = cell.substring(0, dollar),
+            trailing = cell.substring(dollar + math.raw.length),
+        )
+    }
+
+    /**
+     * The index of a `$` that may open math in [cell]: index 0, or the first `$`
+     * when every character before it is opening punctuation. Null otherwise.
+     */
+    private fun mathStartIn(cell: String): Int? {
+        if (cell.isEmpty() || cell[0] == '$') return 0
+        var i = 0
+        while (i < cell.length && isOpeningPunctuation(cell[i])) i++
+        return if (i in 1 until cell.length && cell[i] == '$') i else null
+    }
+
+    /**
+     * Punctuation that commonly opens a wrapped equation in prose. Covers every
+     * Unicode opening bracket and initial quote (so CJK/fullwidth `「『（` work for
+     * a global audience) plus the ASCII straight quotes, which Unicode classes as
+     * generic — not initial — punctuation and so must be named explicitly.
+     */
+    private fun isOpeningPunctuation(c: Char): Boolean =
+        c == '"' ||
+            c == '\'' ||
+            c.category == CharCategory.START_PUNCTUATION ||
+            c.category == CharCategory.INITIAL_QUOTE_PUNCTUATION
 
     /**
      * Splits [line] on single spaces the way `line.split(' ')` would, except that
diff --git a/commons/src/commonMain/kotlin/com/vitorpamplona/amethyst/commons/richtext/RichTextParser.kt b/commons/src/commonMain/kotlin/com/vitorpamplona/amethyst/commons/richtext/RichTextParser.kt
index b5171e8e20..959b8f4a31 100644
--- a/commons/src/commonMain/kotlin/com/vitorpamplona/amethyst/commons/richtext/RichTextParser.kt
+++ b/commons/src/commonMain/kotlin/com/vitorpamplona/amethyst/commons/richtext/RichTextParser.kt
@@ -245,7 +245,7 @@ class RichTextParser {
             val segments =
                 MathParser.split(paragraph.trimEnd()).map { token ->
                     when (token) {
-                        is MathParser.Token.Math -> MathSegment(token.raw, token.latex, token.displayMode, token.trailing)
+                        is MathParser.Token.Math -> MathSegment(token.raw, token.latex, token.displayMode, token.leading, token.trailing)
                         is MathParser.Token.Word -> wordIdentifier(token.text, images, videos, pdfs, urls, emojis, tags)
                     }
                 }
diff --git a/commons/src/commonMain/kotlin/com/vitorpamplona/amethyst/commons/richtext/RichTextParserSegments.kt b/commons/src/commonMain/kotlin/com/vitorpamplona/amethyst/commons/richtext/RichTextParserSegments.kt
index 6b7f6ce993..25d3eae75d 100644
--- a/commons/src/commonMain/kotlin/com/vitorpamplona/amethyst/commons/richtext/RichTextParserSegments.kt
+++ b/commons/src/commonMain/kotlin/com/vitorpamplona/amethyst/commons/richtext/RichTextParserSegments.kt
@@ -175,14 +175,16 @@ class RegularTextSegment(
  *
  * [segmentText] keeps the original text *including* the `$` delimiters so the
  * raw form can be shown as a fallback when rendering fails, while [latex] holds
- * just the inner formula that gets handed to the math renderer. [trailing] is any
- * punctuation glued after the closing `$` (e.g. `.` in `$x$.`), rendered right
- * next to the equation so it doesn't drift off behind a space.
+ * just the inner formula that gets handed to the math renderer. [leading] is any
+ * opening punctuation glued before the opening `$` (e.g. `(` in `($x$)`) and
+ * [trailing] any punctuation glued after the closing `$` (e.g. `.` in `$x$.`),
+ * both rendered right next to the equation so they don't drift off behind a space.
  */
 @Immutable
 class MathSegment(
     segment: String,
     val latex: String,
     val displayMode: Boolean,
+    val leading: String = "",
     val trailing: String = "",
 ) : Segment(segment)
diff --git a/commons/src/commonTest/kotlin/com/vitorpamplona/amethyst/commons/richtext/MathParserTest.kt b/commons/src/commonTest/kotlin/com/vitorpamplona/amethyst/commons/richtext/MathParserTest.kt
index 67dbccf11a..fafd50fdf8 100644
--- a/commons/src/commonTest/kotlin/com/vitorpamplona/amethyst/commons/richtext/MathParserTest.kt
+++ b/commons/src/commonTest/kotlin/com/vitorpamplona/amethyst/commons/richtext/MathParserTest.kt
@@ -177,4 +177,36 @@ class MathParserTest {
         assertEquals("a", m[0].latex)
         assertEquals("b", m[1].latex)
     }
+
+    @Test
+    fun parenWrappedMathIsDetected() {
+        // `($r = 1$)` is the common prose case: the opening paren rides along as
+        // leading, the closing paren as trailing, and the inner span is math.
+        val m = math(MathParser.split("translations (${d}r = 1$d) is cyclic")).single()
+        assertEquals("r = 1", m.latex)
+        assertEquals("(", m.leading)
+        assertEquals(")", m.trailing)
+    }
+
+    @Test
+    fun bracketAndQuoteWrappedMathAreDetected() {
+        val tokens = MathParser.split("see [${d}x$d] and \"${d}y$d\" here")
+        val m = math(tokens)
+        assertEquals(2, m.size)
+        assertEquals("x", m[0].latex)
+        assertEquals("[", m[0].leading)
+        assertEquals("]", m[0].trailing)
+        assertEquals("y", m[1].latex)
+        assertEquals("\"", m[1].leading)
+        assertEquals("\"", m[1].trailing)
+    }
+
+    @Test
+    fun alphanumericGluedPrefixStaysPlainWord() {
+        // A letter before `$` is not opening punctuation, so the existing
+        // glued-word behaviour is preserved (no false-firing on `a$x$`).
+        val tokens = MathParser.split("a${d}x$d" + " end")
+        assertTrue(math(tokens).isEmpty())
+        assertEquals(listOf("a${d}x$d", "end"), tokens.filterIsInstance<Token.Word>().map { it.text })
+    }
 }