修改了nanobot，往Hermes agent的风格走，进度1/3

app-instance/backend-old/nanobot/providers/custom_provider.py

@@ -0,0 +1,61 @@
+"""Direct OpenAI-compatible provider — bypasses LiteLLM."""
+
+from __future__ import annotations
+
+from typing import Any
+
+import json_repair
+from openai import AsyncOpenAI
+
+from nanobot.providers.base import LLMProvider, LLMResponse, ToolCallRequest
+
+
+class CustomProvider(LLMProvider):
+
+    def __init__(
+        self,
+        api_key: str = "no-key",
+        api_base: str = "http://localhost:8000/v1",
+        default_model: str = "default",
+        request_timeout_seconds: float | None = None,
+    ):
+        super().__init__(api_key, api_base, request_timeout_seconds=request_timeout_seconds)
+        self.default_model = default_model
+        self._client = AsyncOpenAI(
+            api_key=api_key,
+            base_url=api_base,
+            timeout=self.request_timeout_seconds,
+        )
+
+    async def chat(self, messages: list[dict[str, Any]], tools: list[dict[str, Any]] | None = None,
+                   model: str | None = None, max_tokens: int = 4096, temperature: float = 0.7) -> LLMResponse:
+        kwargs: dict[str, Any] = {
+            "model": model or self.default_model,
+            "messages": self._sanitize_empty_content(messages),
+            "max_tokens": max(1, max_tokens),
+            "temperature": temperature,
+        }
+        if tools:
+            kwargs.update(tools=tools, tool_choice="auto")
+        try:
+            return self._parse(await self._client.chat.completions.create(**kwargs))
+        except Exception as e:
+            return LLMResponse(content=f"Error: {e}", finish_reason="error")
+
+    def _parse(self, response: Any) -> LLMResponse:
+        choice = response.choices[0]
+        msg = choice.message
+        tool_calls = [
+            ToolCallRequest(id=tc.id, name=tc.function.name,
+                            arguments=json_repair.loads(tc.function.arguments) if isinstance(tc.function.arguments, str) else tc.function.arguments)
+            for tc in (msg.tool_calls or [])
+        ]
+        u = response.usage
+        return LLMResponse(
+            content=msg.content, tool_calls=tool_calls, finish_reason=choice.finish_reason or "stop",
+            usage={"prompt_tokens": u.prompt_tokens, "completion_tokens": u.completion_tokens, "total_tokens": u.total_tokens} if u else {},
+            reasoning_content=getattr(msg, "reasoning_content", None) or None,
+        )
+
+    def get_default_model(self) -> str:
+        return self.default_model