feat/ 导出开发容器内的数据用于评估

api/app/features/evaluation/candidate_runner.py

@@ -0,0 +1,83 @@
+"""独立候选回放：多轮 user 链式调用 LLM，不走路由 WS / ChatOrchestrator。"""
+
+from __future__ import annotations
+
+import time
+from typing import Any
+
+from app.core.logging import get_logger
+
+logger = get_logger(__name__)
+
+
+def _system_prompt_for_eval(version_config: dict | None) -> str:
+    cfg = version_config or {}
+    extra = (cfg.get("system_prompt_suffix") or "").strip()
+    base = """你是「岁月留书」老年友好访谈员。语气温暖、耐心，先承接情绪再 gently 追问事实与感受；回答简洁分段，避免术语。"""
+    if extra:
+        return f"{base}\n\n{extra}"
+    return base
+
+
+def _model_override(version_config: dict | None) -> str | None:
+    if not version_config:
+        return None
+    m = version_config.get("model")
+    return str(m).strip() if m else None
+
+
+class EvalCandidateRunner:
+    """使用 LangChain Chat 模型回放用户轮次。"""
+
+    def __init__(self, llm: Any) -> None:
+        self._llm = llm
+
+    async def replay_utterances(
+        self,
+        utterances: list[str],
+        *,
+        version_config: dict | None = None,
+        temperature: float = 0.7,
+    ) -> tuple[list[str], list[int]]:
+        """返回每轮 assistant 回复与耗时 ms。"""
+        if not self._llm:
+            raise RuntimeError(" replay: llm 未配置")
+        from langchain_core.messages import AIMessage, HumanMessage, SystemMessage
+
+        sys_prompt = _system_prompt_for_eval(version_config)
+        model = _model_override(version_config)
+        lc_messages: list = [SystemMessage(content=sys_prompt)]
+        replies: list[str] = []
+        latencies: list[int] = []
+        bound = (
+            self._llm.bind(model=model, temperature=temperature)
+            if model
+            else self._llm.bind(temperature=temperature)
+        )
+        for u in utterances:
+            text = (u or "").strip()
+            if not text:
+                continue
+            lc_messages.append(HumanMessage(content=text))
+            t0 = time.perf_counter()
+            result = await bound.ainvoke(lc_messages)
+            elapsed_ms = int((time.perf_counter() - t0) * 1000)
+            reply = str(getattr(result, "content", "") or "").strip()
+            replies.append(reply)
+            latencies.append(elapsed_ms)
+            lc_messages.append(AIMessage(content=reply))
+        return replies, latencies
+
+
+def simple_memoir_from_transcript(utterances: list[str], replies: list[str]) -> str:
+    """轻量成稿：供评审用占位（非生产叙事管线）。"""
+    lines = ["# 访谈摘录整理（评测占位稿）", ""]
+    for i, u in enumerate(utterances):
+        lines.append(f"## 片段 {i + 1}")
+        lines.append("")
+        lines.append(f"**用户：** {u.strip()}")
+        if i < len(replies):
+            lines.append("")
+            lines.append(f"**访谈者：** {replies[i].strip()}")
+        lines.append("")
+    return "\n".join(lines)