feat(config): configurable conversation history window (B3)

FastGPT maintains full history server-side; LangGraph truncated the
injected history at a hardcoded 50 messages, so long conversations
behaved differently across backends.

- Config.AGENT_HISTORY_MESSAGES (env): max messages injected into the
  model prompt (recent N, both roles counted); default 50 unchanged;
  larger values support long conversations; 0 = no truncation, matching
  FastGPT's full-history semantics. Only the injected window is
  affected - dialogue stays fully persisted in the checkpoint.
- validate(): rejects negative values; 0 and positive accepted
- conversation_history reads the config (import-time class attribute,
  monkeypatched in tests); explicit None-check keeps 0 falsy-safe
- .env.example documents the knob

Verified: 225 unit tests (6 new history-window tests)

src/agent/collect.py

@@ -108,13 +108,26 @@ async def validated_reply(
     raise CollectReplyError("模型回复格式、阶段转换或时间依据不合规（一次修复后仍失败）")
 
 
-# 工作流 chatNode 的 history 配置为 50；保留独立消息及其角色。
-_HISTORY_MESSAGES = 50
+# 工作流 chatNode 的 history 配置为 50；默认对齐（Config.
+# AGENT_HISTORY_MESSAGES，env 可调大，0 = 不截断对齐 FastGPT 全量语义）。
+_HISTORY_MESSAGES_DEFAULT = 50
 
 
 def conversation_history(state: AgentState) -> list[dict[str, str]]:
-    """历史不拼入 user 消息，不剥除历史 assistant 的状态前缀。"""
-    return [dict(message) for message in (state.get("dialogue") or [])[-_HISTORY_MESSAGES:]]
+    """历史不拼入 user 消息，不剥除历史 assistant 的状态前缀。
+
+    截断窗口取 Config.AGENT_HISTORY_MESSAGES（import 时固化的类属性，
+    测试用 monkeypatch 调整）；0 或负数视为不截断。
+    """
+    from ..core.config import Config
+
+    limit = getattr(Config, "AGENT_HISTORY_MESSAGES", None)
+    if limit is None:
+        limit = _HISTORY_MESSAGES_DEFAULT
+    dialogue = state.get("dialogue") or []
+    if limit > 0:
+        dialogue = dialogue[-limit:]
+    return [dict(message) for message in dialogue]
 
 
 def context_prompt(state: AgentState, *, time_context: dict | None = None) -> str:

src/core/config.py

@@ -33,6 +33,11 @@ class Config:
     # 运行时选择：LLM_PROVIDER=<名>；缺省或 fake = 离线脚本模型。
     LLM_PROVIDERS = os.getenv("LLM_PROVIDERS", "")
     LLM_PROVIDER = os.getenv("LLM_PROVIDER", "")
+    # 对话历史注入模型时的最大消息条数（最近 N 条，双向计数）。
+    # 默认 50（约 25 轮）；调大支持长对话；0 = 不截断（与 FastGPT
+    # 服务端全量历史语义对齐）。对话正文仍随 checkpoint 全量保存，
+    # 本参数只影响注入提示词的历史窗口。
+    AGENT_HISTORY_MESSAGES = int(os.getenv("AGENT_HISTORY_MESSAGES", "50"))
     # LLM 客户端是否信任系统代理（Windows 注册表）。缺省 False：
     # 本地网关（127.0.0.1）必须直连；外部网关若需代理设为 true。
     LLM_HTTP_TRUST_ENV = os.getenv("LLM_HTTP_TRUST_ENV", "false").lower() in (
@@ -149,6 +154,8 @@ class Config:
                 f"Unknown LLM_PROVIDER {cls.LLM_PROVIDER!r}; "
                 f"configured: {sorted(profiles)}"
             )
+        if cls.AGENT_HISTORY_MESSAGES < 0:
+            raise ValueError("AGENT_HISTORY_MESSAGES must be >= 0 (0 = 不截断)")
         if cls.AGENT_BACKEND != "fastgpt":
             return
         required = [