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)

.env.example

@@ -19,6 +19,9 @@ VOICE_CONFIG=config/voice.json
 # 如思考开关 KIMI 网关为 {"reasoning_effort":"none"}）。
 # 超时/重试缺省 60 秒 / 3 次，与 FastGPT 客户端 SLA 对齐
 # （契约测试 test/backends/test_sla_alignment.py）。
+# AGENT_HISTORY_MESSAGES=50：注入模型的对话历史上限（最近 N 条，
+# 双向计数）；调大支持长对话；0 = 不截断（对齐 FastGPT 全量历史）。
+# AGENT_HISTORY_MESSAGES=0
 # LLM_PROVIDERS=deepseek,kimi,gpt6luna
 # LLM_PROVIDER=deepseek
 # LLM_DEEPSEEK_BASE_URL=https://api.openai.com/v1