fix(voice): stop dashboard from mangling the leading [감정] tag

The dashboard voice-turn path ran _speech_text() before MeloTTS.synth, which
rewrote a leading "[힘차게] 안녕!" into "힘차게, 안녕!" — reading the first
emotion aloud and destroying the tag before the TTS emotion parser could use it.
Make _speech_text() a pass-through so every emotion tag (including the first)
reaches synth intact and shapes pitch/speed instead of being spoken. Adds a
regression test covering the leading-tag case.

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

tests/test_emotion.py

@@ -7,6 +7,7 @@ from wsai.backends.emotion import (
     match_emotion,
     parse_segments,
 )
+from wsai.dashboard import _speech_text
 
 BASE = 1.3
 
@@ -74,3 +75,16 @@ def test_persona_examples_are_all_recognised():
     # read aloud instead of shaping the voice.
     for word in ["힘차게", "궁금", "반가움", "차분하게", "웃으며", "속상함"]:
         assert match_emotion(word) is not None, word
+
+
+def test_voice_turn_keeps_leading_emotion_tag_for_tts_parser():
+    text = "[속상함] 정말 힘들었겠다. [힘차게] 하지만 넌 할 수 있어!"
+
+    spoken = _speech_text(text)
+    segs = parse_segments(spoken, BASE)
+
+    assert spoken == text
+    assert segs[0].text == "정말 힘들었겠다."
+    assert segs[0].pitch == EMOTION_PARAMS["sad"][1]
+    assert segs[1].text == "하지만 넌 할 수 있어!"
+    assert segs[1].pitch == EMOTION_PARAMS["hopeful"][1]

wsai/dashboard.py

@@ -18,7 +18,6 @@ from __future__ import annotations
 import json
 import logging
 import queue
-import re
 import threading
 from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
 
@@ -26,20 +25,14 @@ from .monitor import Monitor
 
 log = logging.getLogger("wsai.dashboard")
 
-_EMOTION_RE = re.compile(r"^\s*\[([^\]]+)\]\s*(.*)", re.S)
-
-
 def _speech_text(reply: str) -> str:
-    """Turn a reply like ``[힘차게] 안녕!`` into what the TTS should actually say.
+    """Return reply text exactly as authored for the TTS backend.
 
-    The bracketed emotion is spoken too (per user request), so the leading tag
-    becomes a natural spoken word: ``[힘차게] 안녕!`` -> ``힘차게, 안녕!``. Replies
-    without a tag are spoken as-is."""
-    m = _EMOTION_RE.match(reply or "")
-    if not m:
+    The TTS backend itself understands bracketed emotion tags: known emotion
+    tags steer delivery and are not spoken; non-emotion brackets are spoken.
+    Do not rewrite a leading tag here, or the first emotion would be read aloud
+    and lost before ``MeloTTS.synth`` can parse it."""
     return reply
-    emotion, rest = m.group(1).strip(), m.group(2).strip()
-    return f"{emotion}, {rest}" if rest else emotion
 
 
 def _make_handler(dash: "Dashboard"):