feat(agent): align prompts and runtime with workflow@20261020

- archive workflow/20261020 export (diff vs 20261016: collection prompt
  only - state-decides-body rule, route when info complete)
- prompts: collection.md updated; 6 photo/confirm prompts archived with
  source nodeIds; render_prompt replaces {{$vars}} (Asia/Shanghai clock,
  person fields, explicit 'not provided' for missing prefills)
- llm: message history passed as user/assistant roles (chatNode history=50);
  optional LLM_TEMPERATURE; FakeLLMService supports history-aware responders
- collect: context via system supplement, raw user input as user message
  (Text Editor#2 parity), shared validated_reply (one call, one repair)
- welcome: Assigned Reply#3 original text, stored in dialogue history
- transitions: 2004 plate-confirm entries (2003->2004/2005, 2004->2005)
- verified: prompt files byte-identical to workflow JSON (parametrized test)

src/core/config.py

@@ -27,6 +27,10 @@ class Config:
     LLM_API_KEY = os.getenv("LLM_API_KEY", "")
     LLM_TIMEOUT_SECONDS = float(os.getenv("LLM_TIMEOUT_SECONDS", "30"))
     LLM_MAX_RETRIES = int(os.getenv("LLM_MAX_RETRIES", "2"))
+    # 采样温度；None 表示使用 provider 缺省。对照 FastGPT 应用配置调整。
+    LLM_TEMPERATURE = (
+        float(os.getenv("LLM_TEMPERATURE")) if os.getenv("LLM_TEMPERATURE") else None
+    )
     
     @classmethod
     def validate(cls):