fix(ai-title): 过滤模型「前导思考」，只取标题 (§19.31)

推理型文本模型即便提示词要求「只返回逗号连接的标题」，仍常在标题前先输出
一段思考散文；该散文自身带逗号，直接逗号切分会切出假标题混进结果。切分前
先剥离前导思考（_strip_title_preamble），两层：
- ① 哨兵优先：文本含 ===TITLES===（正则 =+\s*TITLES\s*=+，忽略大小写、
  吞相邻 * / # 装饰）时只取最后一个哨兵之后，思考连同哨兵丢弃
- ② 句号兜底（无需改提示词）：无哨兵时切最后一个 。！？ 及之前；真标题不含
  句末标点，故最后一个句号即前导散文↔标题列表的分界；仅当其后仍含逗号/换行
  分隔符时才剥离，避免末条标题的收尾句号被误当分界清空

- ai_text_service.py：加 _TITLE_SENTINEL / _SENTENCE_END / _strip_title_preamble，
  _clean_titles 切分前调用
- config_service.py：DEFAULT_TITLE_PROMPT 补哨兵约定（思考写最前、单独一行
  ===TITLES===、其后只放逗号标题）
- docs/11 §17.2/§17.3 更新 + 新增 §17.9 决策；tasks.md §19.31
- 不碰 packaging/default_config/title_prompt.txt（用户精细模板，并行未提交）

验证：test_ai_text_service（22）+ 全套 py37（236 测试）通过，唯一失败为
无关的 test_config_service packaging 模板；离屏冒烟用真实返回样本 → 前导思考
被剥离、取全部干净标题，默认提示词含哨兵。

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

src/services/ai_text_service.py

@@ -36,6 +36,13 @@ _TITLE_CIRCLED = "①②③④⑤⑥⑦⑧⑨⑩"
 _TITLE_QUOTES = "\"'「」『』“”‘’"
 # Split titles on comma (half/full width) or newline (docs/11 §17.1 / §19.23).
 _TITLE_SPLIT = re.compile(r"[,，\r\n]+")
+# Sentinel the prompt asks the model to print after any "thinking" preamble;
+# everything after the last sentinel is the title list (docs/11 §17.3 / §17.9).
+# Tolerant: matches ===TITLES===, ==TITLES==, **===TITLES===**… case-insensitively,
+# consuming adjacent markdown decoration (* / #) so it never leaks into the tail.
+_TITLE_SENTINEL = re.compile(r"[*#]*\s*=+\s*TITLES\s*=+\s*[*#]*", re.IGNORECASE)
+# Sentence-ending punctuation marking the end of a prose preamble (§17.9 fallback).
+_SENTENCE_END = "。！？"
 
 
 def build_text_payload(config, prompt, image_data_url=None):
@@ -130,17 +137,47 @@ def _clean_title_line(line):
     return stripped
 
 
+def _strip_title_preamble(text):
+    """Drop a leading "thinking" preamble so only the title list remains (§17.9).
+
+    Reasoning models often emit prose before the titles even when told not to;
+    that prose carries commas, so comma-splitting it yields fake titles. Two
+    layers, in priority order:
+
+    1. Sentinel (deterministic): if the prompt-agreed `===TITLES===` marker is
+       present, keep only what follows the LAST sentinel — thinking (and the
+       marker) is discarded.
+    2. Sentence-end fallback (no prompt change needed): otherwise cut everything
+       up to and including the last `。！？`. Real titles carry no sentence-ending
+       punctuation (the prompt forbids it), so the last one marks the prose↔list
+       boundary. Only strip when a title separator (`,`/`，`/newline) still
+       remains after it — else the `。` was a lone trailing mark, not a boundary,
+       and stripping would wipe the titles.
+    """
+    s = str(text)
+    matches = list(_TITLE_SENTINEL.finditer(s))
+    if matches:
+        return s[matches[-1].end():]
+    cut = max((s.rfind(ch) for ch in _SENTENCE_END), default=-1)
+    if cut != -1:
+        tail = s[cut + 1:]
+        if _TITLE_SPLIT.search(tail):
+            return tail
+    return s
+
+
 def _clean_titles(text):
     """Split raw text into a list of cleaned titles, on comma (or newline).
 
     The prompt asks the model to comma-separate titles (docs/11 §17.1 / §19.23);
     splitting on `,`/`，`/newline avoids the Markdown-table mis-parse that line
-    splitting produced.
+    splitting produced. A leading model "thinking" preamble is stripped first
+    (`_strip_title_preamble`, §17.9) so it never leaks in as fake titles.
     """
     if not text:
         return []
     out = []
-    for piece in _TITLE_SPLIT.split(str(text)):
+    for piece in _TITLE_SPLIT.split(_strip_title_preamble(text)):
         cleaned = _clean_title_line(piece)
         if cleaned:
             out.append(cleaned)

src/services/config_service.py

@@ -49,8 +49,10 @@ DEFAULT_OUTFIT_PROMPT = (
 DEFAULT_TITLE_PROMPT = (
     "请生成 10 条适合台湾蝦皮电商的中文女装商品标题，突出卖点与适穿场景，"
     "每条控制在 30 字以内。"
-    "标题之间用逗号「，」分隔，只输出标题本身，"
-    "不要使用 Markdown 表格、不要换行、不要序号/編號/字元數、不要引号或表情。"
+    "如果你需要思考或说明，请全部写在最前面；思考完毕后单独一行输出 ===TITLES===，"
+    "其后只放所有标题、标题之间用逗号「，」分隔。"
+    "===TITLES=== 之后不要出现任何非标题文字，"
+    "不要使用 Markdown 表格、不要序号/編號/字元數、不要引号或表情。"
 )