feat(api): 叙事 prompt、职业上下文、读路径章节、WS 解耦与错误脱敏

- 回忆录：事实边界补充允许清单；传记文体示例与 JSON 叙事要求对齐
- default 职业提示 occupation_context；cadre/military 退休语境
- GET 章节读路径零写入，prepare_chapter_read_view + markdown_for_response
- 文本归一抽到 core/text_normalize；移除弃用 reply 策略与 recompose_chapters_for_story
- ConversationService：WS 连接/用户段落/结束对话；对外错误固定文案
- 测试：HTTP 脱敏契约、章节读视图、occupation 与 background_voice

api/app/features/memoir/story_pipeline_sync.py

@@ -33,7 +33,7 @@ from app.features.memoir.memoir_images.settings import MemoirImageSettings
 from app.features.memoir.models import Chapter
 from app.features.memoir.narrative_to_markdown import narrative_to_markdown
 from app.features.memoir.oral_normalize import (
-    apply_oral_normalization_rules,
+    apply_oral_rules,
     normalize_oral_for_memoir,
 )
 from app.features.memoir.repo import (
@@ -63,7 +63,7 @@ def _route_segment_texts(category_segments: list) -> list[tuple[str, str]]:
             and (settings.memoir_oral_normalize_mode or "rules").strip().lower()
             != "off"
         ):
-            t = apply_oral_normalization_rules(raw)
+            t = apply_oral_rules(raw)
         else:
             t = raw
         out.append((str(seg.id), t))
@@ -312,6 +312,7 @@ def _run_batch_plan_writes(
     llm: Any,
     narrative_agent: NarrativeAgent,
     background_voice: str = "default",
+    occupation: str = "",
 ) -> set[str]:
     dispatch_ids: set[str] = set()
     max_chars = int(settings.story_append_max_canonical_chars)
@@ -362,6 +363,7 @@ def _run_batch_plan_writes(
             birth_year=user_birth_year,
             llm=llm,
             background_voice=background_voice,
+            occupation=occupation,
         )
         json_invalid = False
         s0 = (raw_gen or "").strip()
@@ -461,6 +463,7 @@ def run_story_pipeline_for_category_batch(
     user_birth_year: int | None,
     llm: Any,
     background_voice: str = "default",
+    occupation: str = "",
 ) -> tuple[Chapter | None, bool, set[str]]:
     """
     返回 (chapter, needs_cover_enqueue, story_ids_to_dispatch_after_commit)。
@@ -589,6 +592,7 @@ def run_story_pipeline_for_category_batch(
             llm=llm,
             narrative_agent=narrative_agent,
             background_voice=background_voice,
+            occupation=occupation,
         )
     else:
         route = route_agent.decide(
@@ -636,6 +640,7 @@ def run_story_pipeline_for_category_batch(
             birth_year=user_birth_year,
             llm=llm,
             background_voice=background_voice,
+            occupation=occupation,
         )
         json_invalid = False
         s0 = (raw_gen or "").strip()