feat(inference): 接通真实 LLM 引擎工厂（P5-T10 门禁接线）

- 新增 inference/factory.build_inference_engine：读 GENESIS_INFERENCE__* / 裸
  DEEPSEEK_API_KEY·LLM_BASE_URL 环境变量与 .env，构造 HttpLLMClient + InferenceEngine
- orchestrator/qa_loop 的 engine=None 分支改用工厂，真正接通真实 LLM 路径
- 脚本注入校验改为通用（非空段落数 + 残留占位符），适配真实模式
- 补工厂测试（缺密钥/前缀变量/裸变量/默认值/.env 解析），覆盖率 99.04%

src/genesis/qa/qa_loop.py

@@ -3,7 +3,7 @@ from __future__ import annotations
 
 from pathlib import Path
 
-from genesis.inference.engine import InferenceEngine
+from genesis.inference.factory import build_inference_engine
 from genesis.inference.prompt_registry import PromptRegistry
 from genesis.qa.guardrails import DEFAULT_MAX_QA_ROUNDS, QALoopController
 from genesis.qa.report import QAReport
@@ -47,7 +47,7 @@ class QALoop:
         return [contents_map[cid] for cid in order]
 
     def run(self, structured_source, output_path, session_id="writer", samples_dir="samples", engine=None, prompt_registry=None, template_path=None) -> QAReport:
-        engine = engine or InferenceEngine()
+        engine = engine or build_inference_engine()
         prompt_registry = prompt_registry or PromptRegistry()
         validator = QAValidator()
         contents = self._build(structured_source, samples_dir, engine, prompt_registry, template_path, output_path, session_id)