feat: jc 引擎主线搬入 app/engine（315 测试基线全绿：320 去掉 admin 5 用例）

Co-Authored-By: Claude Code <noreply@anthropic.com>

app/engine/providers/base.py

@@ -0,0 +1,24 @@
+from abc import ABC, abstractmethod
+from collections.abc import AsyncGenerator
+
+
+class AIProvider(ABC):
+    @abstractmethod
+    async def chat(self, messages: list[dict], system_prompt: str) -> str:
+        """Send messages and return assistant reply text."""
+
+    @abstractmethod
+    async def stream_chat(
+        self, messages: list[dict], system_prompt: str
+    ) -> AsyncGenerator[str, None]:
+        """Stream assistant reply token by token."""
+
+    @abstractmethod
+    async def chat_with_extraction(
+        self, messages: list[dict], system_prompt: str
+    ) -> tuple[str, dict]:
+        """Send messages and return (reply_text, extracted_json).
+
+        The provider should request JSON output and parse it.
+        Falls back to empty dict if parsing fails.
+        """

app/engine/providers/glm.py

@@ -0,0 +1,94 @@
+import asyncio
+import json
+import logging
+from collections.abc import AsyncGenerator
+
+from zhipuai import ZhipuAI
+
+from app.engine.providers.base import AIProvider
+
+logger = logging.getLogger(__name__)
+
+DEFAULT_MODEL = "glm-4-flash"
+
+
+class GLMProvider(AIProvider):
+    def __init__(self, api_key: str, model: str = "glm-4-flash", base_url: str = ""):
+        self.client = ZhipuAI(api_key=api_key, base_url=base_url or None)
+        self.model = model
+
+    async def chat(self, messages: list[dict], system_prompt: str) -> str:
+        full_messages = [{"role": "system", "content": system_prompt}] + messages
+        return await self._call(full_messages, temperature=0.3)
+
+    async def stream_chat(
+        self, messages: list[dict], system_prompt: str
+    ) -> AsyncGenerator[str, None]:
+        full_messages = [{"role": "system", "content": system_prompt}] + messages
+
+        def _sync_stream():
+            resp = self.client.chat.completions.create(
+                model=self.model,
+                messages=full_messages,
+                stream=True,
+                temperature=0.3,
+            )
+            for chunk in resp:
+                delta = chunk.choices[0].delta
+                if delta and delta.content:
+                    yield delta.content
+
+        try:
+            loop = asyncio.get_event_loop()
+            gen = _sync_stream()
+
+            def _next_token(g):
+                try:
+                    return next(g)
+                except StopIteration:
+                    return None
+
+            while True:
+                token = await loop.run_in_executor(None, _next_token, gen)
+                if token is None:
+                    break
+                yield token
+        except Exception:
+            logger.exception("GLM streaming call failed")
+            raise
+
+    async def chat_with_extraction(
+        self, messages: list[dict], system_prompt: str
+    ) -> tuple[str, dict]:
+        full_messages = [{"role": "system", "content": system_prompt}] + messages
+        if not messages:
+            full_messages.append({"role": "user", "content": "请根据以上要求输出结果。"})
+
+        raw = await self._call(full_messages, temperature=0.1)
+        extracted = self._parse_json(raw)
+        return raw, extracted
+
+    async def _call(self, messages: list[dict], temperature: float = 0.3) -> str:
+        def _sync_call():
+            resp = self.client.chat.completions.create(
+                model=self.model,
+                messages=messages,
+                temperature=temperature,
+            )
+            return resp.choices[0].message.content
+
+        try:
+            return await asyncio.to_thread(_sync_call)
+        except Exception:
+            logger.exception("GLM API call failed")
+            raise
+
+    @staticmethod
+    def _parse_json(text: str) -> dict:
+        try:
+            start = text.index("{")
+            end = text.rindex("}") + 1
+            return json.loads(text[start:end])
+        except (ValueError, json.JSONDecodeError):
+            logger.warning("Failed to parse JSON from model output")
+            return {}