feat: InferenceEngine chat/chat_structured 全流程 + 文档补丁（补丁1/2/3）

tests/inference_helpers.py

@@ -0,0 +1,27 @@
+from __future__ import annotations
+
+from genesis.inference.types import TokenUsage
+
+
+class FakeLLMClient:
+    """可编程的假 LLM 客户端：记录调用，按脚本返回（离线）。"""
+
+    def __init__(self, script=None):
+        # script: list[(status, content)]；status: "ok" | "raise_timeout" | "raise_network" | "parse_fail"
+        self.script = script or [("ok", "hello")]
+        self.calls: list[dict] = []
+
+    def chat(self, *, model, messages, temperature, max_tokens):
+        self.calls.append({"model": model, "messages": [m.content for m in messages]})
+        status, content = self.script.pop(0)
+        if status == "raise_timeout":
+            from genesis.inference.exceptions import LLMTimeoutError
+
+            raise LLMTimeoutError("timeout")
+        if status == "raise_network":
+            from genesis.inference.exceptions import LLMNetworkError
+
+            raise LLMNetworkError("network")
+        if status == "parse_fail":
+            content = "NOT JSON"
+        return content, TokenUsage(input_tokens=10, output_tokens=2)