feat: 大模型使用场景化配置与去重多源记录

- 新增 configs/llm_models.yaml: 4 个场景(event_extraction/daily_report/stock_report/embedding)
  可独立配置 provider/model/api_key_env/base_url_env/temperature 等,含用途与模型要求说明
- 新增 configs/loader.py: YAML 场景加载器(优先级: CLI 参数 > YAML > .env > 内置默认)
- llm/client.py: load_llm_config 支持 scene 参数,LLMConfig 增加 max_attempts
- embedding/factory+remote+local: provider/model/batch_limit 支持场景覆盖
- scheduler/reporter+stock_reporter: 日报/个股摘要接入场景配置
- dedup: Fingerprint.source_ids 多源记录 + 旧库自动迁移 + DedupResult 多源字段
- scripts/run_dedup: uniques JSON 的 sources 字段 + data/deduped/{day}/sources.json 汇总
- scripts/run_event_extraction: 接入 event_extraction 场景
- 补充测试: 场景优先级/零值、多源合并、旧库迁移、embedding 场景覆盖

llm/__init__.py

@@ -8,15 +8,18 @@
 """
 
 from .client import (
+    DEFAULT_MAX_ATTEMPTS,
     DEFAULT_TEMPERATURE,
     DEFAULT_TIMEOUT_SEC,
+    SCENE_DAILY_REPORT,
+    SCENE_EVENT_EXTRACTION,
+    SCENE_STOCK_REPORT,
     LLMConfig,
     load_llm_config,
     make_async_client,
     make_sync_client,
 )
 from .extractor import (
-    DEFAULT_MAX_ATTEMPTS,
     DEFAULT_PROMPT_PATH,
     MAX_CONTENT_CHARS,
     PromptTemplate,
@@ -43,6 +46,9 @@ __all__ = [
     "MAX_CONTENT_CHARS",
     "MAX_IMPORTANCE",
     "MIN_IMPORTANCE",
+    "SCENE_DAILY_REPORT",
+    "SCENE_EVENT_EXTRACTION",
+    "SCENE_STOCK_REPORT",
     "EventExtraction",
     "ExtractedEvent",
     "LLMCallError",