refactor: centralize llm provider transport

app/backend/features/mentor/agent.py

@@ -3,14 +3,12 @@ from __future__ import annotations
 import json
 import re
 import time
-import urllib.error
-import urllib.request
 from collections.abc import Iterator
 from dataclasses import dataclass
 from pathlib import Path
 from typing import Any
 
-from llm_stream import OpenAIStreamAccumulator
+from backend.llm import transport as llm_transport
 
 
 class MentorAgentError(RuntimeError):
@@ -195,50 +193,20 @@ def stream_with_mentor(
     messages = [{"role": "system", "content": system_prompt}]
     messages.extend(history[-10:])
     messages.append({"role": "user", "content": question})
-    payload = json.dumps(
-        {"model": model, "messages": messages, "stream": True},
-        ensure_ascii=False,
-    ).encode("utf-8")
-    request = urllib.request.Request(
-        f"{base_url.rstrip('/')}/chat/completions",
-        data=payload,
-        headers={
-            "Content-Type": "application/json",
-            "Authorization": f"Bearer {api_key}",
-            "User-Agent": "XiaobaiReviewWeb/0.6",
-            "Accept": "text/event-stream",
-        },
-        method="POST",
-    )
     try:
-        with urllib.request.urlopen(request, timeout=timeout) as response:
-            yielded = False
-            accumulator = OpenAIStreamAccumulator()
-            for raw_line in response:
-                line = raw_line.decode("utf-8", errors="replace").strip()
-                if not line or line.startswith(":"):
-                    continue
-                if line.startswith("data:"):
-                    line = line[5:].strip()
-                if line == "[DONE]":
-                    break
-                try:
-                    result = json.loads(line)
-                except json.JSONDecodeError:
-                    continue
-                choices = result.get("choices") or []
-                if not choices:
-                    continue
-                choice = choices[0] or {}
-                content = accumulator.feed(choice)
-                if content:
-                    yielded = True
-                    yield str(content)
-            if not yielded:
-                raise MentorAgentError("问师模型未返回有效内容。")
-    except urllib.error.HTTPError as exc:
-        raise MentorAgentError(_http_error_message(exc)) from exc
-    except (urllib.error.URLError, TimeoutError, OSError) as exc:
+        yield from llm_transport.stream_chat_completion(
+            api_key=api_key,
+            base_url=base_url,
+            model=model,
+            messages=messages,
+            timeout=timeout,
+            user_agent="XiaobaiReviewWeb/0.6",
+        )
+    except llm_transport.OpenAIEmptyResponseError as exc:
+        raise MentorAgentError("问师模型未返回有效内容。") from exc
+    except llm_transport.OpenAIHTTPError as exc:
+        raise MentorAgentError(exc.describe("问师模型调用失败")) from exc
+    except llm_transport.OpenAITransportError as exc:
         raise MentorAgentError(f"问师模型调用失败：{exc}") from exc
 
 
@@ -298,20 +266,3 @@ def _parse_frontmatter(content: str) -> dict[str, str]:
 def _first_sentence(text: str) -> str:
     compact = " ".join(line.strip() for line in text.splitlines() if line.strip())
     return re.split(r"[。；]", compact, maxsplit=1)[0].strip()
-
-
-def _http_error_message(exc: urllib.error.HTTPError) -> str:
-    detail = ""
-    try:
-        payload = json.loads(exc.read().decode("utf-8", errors="replace"))
-        error = payload.get("error")
-        if isinstance(error, dict):
-            detail = str(error.get("message") or error.get("code") or "")
-        elif error:
-            detail = str(error)
-        elif payload.get("message"):
-            detail = str(payload["message"])
-    except (json.JSONDecodeError, OSError):
-        detail = ""
-    suffix = f"：{detail[:300]}" if detail else ""
-    return f"问师模型调用失败（HTTP {exc.code}）{suffix}"