fix(bridge): keep decimals, versions and URLs whole in TTS sentence split

The streaming splitter treated every "." as a sentence boundary, so the
operational reply "17.5°C" was read as "17." / "5°C" and "1.8 km/h" as
"1." / "8 km/h" - numbers spoken digit-by-digit plus extra TTS calls.

An ASCII terminator (. ! ?) now only ends a sentence when it is followed by
whitespace, a closing quote/bracket, or end of text. In-token dots (decimals
"17.5", versions "v2.0", hosts "example.com") are followed by a digit/letter,
so they no longer split. CJK fullwidth terminators stay unconditional since
those scripts use no trailing space. Language-agnostic, punctuation only.

- bridge: lookahead-gated boundary regex + finditer-based chunking
- tests: regression cases for decimals (17.5/1.8), versions, URLs, and an
  integer that genuinely ends a sentence

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

bridge/text_utils.py

@@ -9,38 +9,63 @@ from __future__ import annotations
 import re
 from typing import List, Optional
 
-# Sentence terminators across scripts: ASCII . ! ? plus the CJK fullwidth forms
+# A sentence boundary is one of:
-# and the ellipsis. Runs of terminators ("?!", "...") collapse into one boundary.
+#   - a run of newlines, OR
-# A run of newlines is also a boundary. This is punctuation-only and therefore
+#   - a run of CJK fullwidth terminators (。！？) / the ellipsis (…) - these are
-# language-agnostic (no hardcoded words), per the project's multilingual rule.
+#     ALWAYS boundaries because CJK scripts put no space after a sentence, OR
-_BOUNDARY = re.compile(r"([.!?。！？…]+|\n+)")
+#   - a run of ASCII terminators (. ! ?) that actually ENDS a sentence, i.e. is
+#     followed by whitespace, a closing quote/bracket, or the end of the text.
+#
+# Requiring that trailing whitespace/end for ASCII terminators is what keeps
+# in-token dots from being mistaken for sentence ends, language-agnostically:
+#   - decimals  -> "17.5°C", "1.8 km/h": the dot is followed by a digit, no space
+#   - versions  -> "v2.0", "3.14": same
+#   - URLs/hosts-> "example.com/path": the dots are followed by letters, no space
+# so none of them match and the number/URL stays inside a single spoken chunk.
+# This is punctuation-only (no hardcoded words), per the project's multilingual
+# rule. Runs of terminators ("?!", "...") still collapse into one boundary.
+_BOUNDARY = re.compile(
+    r"""
+      (?P<nl>\n+)                          # a run of newlines
+    | (?P<cjk>[。！？…]+)                    # CJK terminators: always end a sentence
+    | (?P<ascii>[.!?]+)                     # ASCII terminator run...
+        (?=[)\]"'”’》」』]*(?:\s|$))          # ...only at a real sentence end
+    """,
+    re.VERBOSE,
+)
 
 
 def split_sentences(text: Optional[str], min_len: int = 5) -> List[str]:
     """Split ``text`` into sentence-sized chunks for streaming TTS.
 
     Each chunk ends at a sentence boundary so it can be synthesised and played
-    while later chunks are still being spoken. Fragments shorter than
+    while later chunks are still being spoken. Sentence boundaries are detected
-    ``min_len`` characters (interjections like "네.", "응") are merged into an
+    on terminal punctuation only (language-agnostic). Dots that live *inside* a
-    adjacent chunk so we don't emit choppy micro-clips. Returns an empty list
+    token - decimal points ("17.5"), version numbers ("v2.0") and URLs
-    for blank input and never loses visible content.
+    ("example.com") - are NOT boundaries, so numbers and links are spoken in one
+    piece instead of being chopped digit-by-digit.
+
+    Fragments shorter than ``min_len`` characters (interjections like "네.", and
+    single-letter initials like "J.") are merged into an adjacent chunk so we
+    don't emit choppy micro-clips. Returns an empty list for blank input and
+    never loses visible content.
     """
     text = (text or "").strip()
     if not text:
         return []
 
-    parts = _BOUNDARY.split(text)
     chunks: List[str] = []
     buf = ""
-    for i in range(0, len(parts), 2):
+    last = 0
-        seg = parts[i]
+    for m in _BOUNDARY.finditer(text):
-        delim = parts[i + 1] if i + 1 < len(parts) else ""
+        buf += text[last:m.end()]
-        buf += seg + delim
+        last = m.end()
         # Flush at a real boundary once the buffer is a worthwhile clip.
-        if delim and len(buf.strip()) >= min_len:
+        if len(buf.strip()) >= min_len:
             chunks.append(buf.strip())
             buf = ""
 
+    buf += text[last:]
     tail = buf.strip()
     if tail:
         if chunks and len(tail) < min_len:

tests/test_bridge_sentence_split.py

@@ -75,3 +75,40 @@ def test_chunks_preserve_all_visible_content_in_order():
 def test_collapses_repeated_terminators_into_one_chunk():
     chunks = split_sentences("정말요?! 네 맞습니다.")
     assert chunks == ["정말요?!", "네 맞습니다."]
+
+
+@pytest.mark.unit
+def test_decimal_point_is_not_a_sentence_boundary():
+    # Regression: "17.5" / "1.8" used to split as "17." / "5" and "1." / "8",
+    # making the TTS read numbers digit-by-digit. The decimal dot is followed by
+    # a digit (no space), so it must stay inside one chunk.
+    assert split_sentences("현재 기온은 17.5도입니다.") == ["현재 기온은 17.5도입니다."]
+    assert split_sentences("바람은 1.8 km/h입니다.") == ["바람은 1.8 km/h입니다."]
+
+
+@pytest.mark.unit
+def test_decimals_across_two_sentences_split_only_at_the_real_end():
+    chunks = split_sentences("기온은 17.5도입니다. 바람은 1.8 km/h입니다.")
+    assert chunks == ["기온은 17.5도입니다.", "바람은 1.8 km/h입니다."]
+
+
+@pytest.mark.unit
+def test_english_decimal_and_version_numbers_stay_whole():
+    assert split_sentences("Pi is about 3.14 today.") == ["Pi is about 3.14 today."]
+    assert split_sentences("Upgrade to v2.0 now.") == ["Upgrade to v2.0 now."]
+
+
+@pytest.mark.unit
+def test_url_dots_are_not_boundaries():
+    # Dots inside a host/path are followed by letters, not whitespace, so the
+    # link is spoken in one piece; only the trailing sentence dot splits.
+    chunks = split_sentences("Visit example.com for details. Thanks!")
+    assert chunks == ["Visit example.com for details.", "Thanks!"]
+
+
+@pytest.mark.unit
+def test_integer_at_sentence_end_still_splits():
+    # A dot after a number that genuinely ends a sentence (followed by a space)
+    # is still a boundary - only the *internal* decimal dot is protected.
+    chunks = split_sentences("I scored 5. Next round now.")
+    assert chunks == ["I scored 5.", "Next round now."]