309a051038
数据库与模型：新增多版迁移（章节证据快照、对话血缘、记忆事实/时间线 lineage 等），把「成稿 ↔ 对话/记忆」的溯源信息落到表结构里。 业务链路：会话与 WS、回忆录/故事流水线、记忆写入与 enrichment 等跟着接上线索与快照；新增章节证据快照与评测侧 EvalTraceService 等模块，方便组评审用的证据包。 内部评测：自动化 run 与手工 memoir 评审共用可追溯证据；rubric/ judge 相关脚本与文档有配套调整。 app-eval-web：Memoir/实验详情里能展开看证据摘要与 evidence_trace（含对话轮次 id）；Vite 代理与 development.sh 注入的 API 端口与当前默认内部评测端口一致，避免改端口后页面连错服务。 工程杂项：GitHub Actions / 仓库说明有更新；各适配器与支付/配额/plan 等多处为小改动或跟随主改动的收尾；新增/扩充了?
296 lines
11 KiB
Python
296 lines
11 KiB
Python
"""
|
||
ProfileAgent：用户资料收集 Specialist
|
||
负责提取资料、资料追问、资料收集开场白，不负责 Redis 持久化（由 Orchestrator 统一处理）
|
||
"""
|
||
|
||
import time
|
||
from typing import Any, Dict, List, Optional
|
||
|
||
from langchain_core.messages import AIMessage, HumanMessage, SystemMessage
|
||
|
||
from app.agents.chat.helpers import format_history_string, get_history_with_window
|
||
from app.agents.chat.prompts_profile import (
|
||
get_profile_extraction_prompt,
|
||
get_profile_followup_prompt,
|
||
get_profile_greeting_prompt,
|
||
)
|
||
from app.agents.chat.reply_limits import (
|
||
nonempty_segments_or_fallback,
|
||
segments_from_llm_response,
|
||
truncate_chat_segments,
|
||
)
|
||
from app.agents.chat.schemas import ProfileExtractionOutput
|
||
from app.core.agent_logging import agent_span, log_agent_payload, log_agent_summary
|
||
from app.core.config import settings
|
||
from app.core.dependencies import get_llm_provider
|
||
from app.core.llm_call import allm_json_call
|
||
from app.core.logging import get_logger
|
||
|
||
logger = get_logger(__name__)
|
||
|
||
|
||
def _get_langchain_llm():
|
||
try:
|
||
provider = get_llm_provider()
|
||
return getattr(provider, "langchain_llm", None)
|
||
except Exception:
|
||
return None
|
||
|
||
|
||
def _message_contents_char_count(messages: List[Any]) -> int:
|
||
n = 0
|
||
for m in messages:
|
||
c = getattr(m, "content", None)
|
||
if isinstance(c, str):
|
||
n += len(c)
|
||
return n
|
||
|
||
|
||
class ProfileAgent:
|
||
"""用户资料收集 Specialist Agent"""
|
||
|
||
def __init__(self):
|
||
self.llm = _get_langchain_llm()
|
||
|
||
async def _invoke_chat(
|
||
self,
|
||
messages: List[Any],
|
||
*,
|
||
max_tokens: int,
|
||
conversation_id: Optional[str],
|
||
agent_name: str,
|
||
) -> str:
|
||
chat_llm = self.llm.bind(max_tokens=max_tokens)
|
||
llm_t0 = time.perf_counter()
|
||
with agent_span(
|
||
logger, f"{agent_name}.llm", conversation_id=conversation_id or ""
|
||
):
|
||
response = await chat_llm.ainvoke(messages)
|
||
logger.info(
|
||
"event=chat_llm_done agent={} response_latency_ms={:.2f}",
|
||
agent_name,
|
||
(time.perf_counter() - llm_t0) * 1000,
|
||
)
|
||
return (
|
||
response.content if hasattr(response, "content") else str(response)
|
||
) or ""
|
||
|
||
async def _segments_from_response(
|
||
self,
|
||
response_text: str,
|
||
*,
|
||
max_segments: int,
|
||
max_chars_per_segment: int,
|
||
fallback: str,
|
||
) -> List[str]:
|
||
log_agent_payload(
|
||
logger,
|
||
"ProfileAgent._segments_from_response.raw_response",
|
||
response_text,
|
||
)
|
||
raw_list = segments_from_llm_response(response_text, max_segments=max_segments)
|
||
if not raw_list:
|
||
raw_list = [response_text.strip()]
|
||
out = truncate_chat_segments(
|
||
raw_list,
|
||
max_segments=max_segments,
|
||
max_chars_per_segment=max_chars_per_segment,
|
||
)
|
||
segments = out if out else [response_text.strip()[:max_chars_per_segment]]
|
||
return nonempty_segments_or_fallback(segments, fallback=fallback)
|
||
|
||
async def extract_profile_from_message(
|
||
self,
|
||
user_message: str,
|
||
missing_fields: List[str],
|
||
conversation_id: Optional[str] = None,
|
||
) -> Dict[str, Any]:
|
||
"""从用户消息中提取资料字段，不持久化"""
|
||
if not self.llm or not missing_fields:
|
||
return {}
|
||
recent_dialogue = ""
|
||
if conversation_id:
|
||
hw = await get_history_with_window(
|
||
conversation_id,
|
||
max_pairs=settings.chat_history_max_pairs,
|
||
max_chars=settings.chat_history_max_chars,
|
||
)
|
||
recent = hw.window[-4:] if len(hw.window) > 4 else hw.window
|
||
parts = []
|
||
for msg in recent:
|
||
if isinstance(msg, HumanMessage):
|
||
parts.append(f"用户: {msg.content}")
|
||
elif isinstance(msg, AIMessage):
|
||
parts.append(f"助手: {msg.content}")
|
||
recent_dialogue = "\n".join(parts) if parts else ""
|
||
try:
|
||
prompt = get_profile_extraction_prompt(
|
||
user_message, missing_fields, recent_dialogue=recent_dialogue or None
|
||
)
|
||
parsed = await allm_json_call(
|
||
self.llm,
|
||
prompt,
|
||
ProfileExtractionOutput,
|
||
max_tokens=settings.chat_profile_extract_max_tokens,
|
||
agent="ProfileAgent.extract_profile_from_message",
|
||
fallback_factory=lambda: ProfileExtractionOutput(),
|
||
)
|
||
result = {}
|
||
if parsed.birth_year is not None:
|
||
raw = parsed.birth_year
|
||
if isinstance(raw, int) and 1900 <= raw <= 2100:
|
||
result["birth_year"] = raw
|
||
elif isinstance(raw, str) and raw.isdigit():
|
||
y = int(raw)
|
||
if y < 100:
|
||
y = 1900 + y if y >= 50 else 2000 + y
|
||
if 1900 <= y <= 2100:
|
||
result["birth_year"] = y
|
||
if parsed.birth_place:
|
||
result["birth_place"] = str(parsed.birth_place)
|
||
if parsed.grew_up_place:
|
||
result["grew_up_place"] = str(parsed.grew_up_place)
|
||
if parsed.occupation:
|
||
result["occupation"] = str(parsed.occupation)
|
||
bp = result.get("birth_place")
|
||
gp = result.get("grew_up_place")
|
||
if bp and not gp:
|
||
result["grew_up_place"] = bp
|
||
elif gp and not bp:
|
||
result["birth_place"] = gp
|
||
return result
|
||
except Exception as e:
|
||
logger.error("提取资料信息失败: {}", e)
|
||
return {}
|
||
|
||
async def generate_profile_followup(
|
||
self,
|
||
conversation_id: str,
|
||
user_message: str,
|
||
missing_fields: List[str],
|
||
filled_fields: Dict[str, str],
|
||
nickname: str = "",
|
||
interview_stage_hint: str = "",
|
||
) -> List[str]:
|
||
"""生成资料追问回复，不持久化（由 Orchestrator 负责）"""
|
||
if not self.llm:
|
||
return ["谢谢！还能告诉我更多吗？"]
|
||
try:
|
||
prompt = get_profile_followup_prompt(
|
||
missing_fields,
|
||
filled_fields,
|
||
nickname,
|
||
interview_stage_hint=interview_stage_hint,
|
||
)
|
||
hw = await get_history_with_window(
|
||
conversation_id,
|
||
max_pairs=settings.chat_history_max_pairs,
|
||
max_chars=settings.chat_history_max_chars,
|
||
)
|
||
messages: List[Any] = [SystemMessage(content=prompt)]
|
||
messages.extend(hw.window)
|
||
messages.append(HumanMessage(content=user_message))
|
||
log_agent_payload(
|
||
logger,
|
||
"ProfileAgent.followup.prompt",
|
||
format_history_string(
|
||
messages,
|
||
omit_system_body=settings.agent_log_omit_system_message_body,
|
||
),
|
||
)
|
||
prompt_chars = _message_contents_char_count(messages)
|
||
logger.info(
|
||
"event=chat_prompt_built agent=ProfileAgent.generate_profile_followup "
|
||
"prompt_chars={} history_pairs_total={} history_pairs_windowed={}",
|
||
prompt_chars,
|
||
hw.turn_total,
|
||
len(hw.window) // 2,
|
||
)
|
||
response_text = await self._invoke_chat(
|
||
messages,
|
||
max_tokens=settings.chat_profile_followup_max_tokens,
|
||
conversation_id=conversation_id,
|
||
agent_name="ProfileAgent.generate_profile_followup",
|
||
)
|
||
segments = await self._segments_from_response(
|
||
response_text,
|
||
max_segments=3,
|
||
max_chars_per_segment=settings.chat_interview_max_chars_per_segment,
|
||
fallback="谢谢分享！能再告诉我一些吗？",
|
||
)
|
||
log_agent_summary(
|
||
logger,
|
||
"ProfileAgent.followup segments={} conversation_id={}",
|
||
len(segments),
|
||
conversation_id,
|
||
)
|
||
return segments
|
||
except Exception as e:
|
||
logger.error("生成资料跟进回复失败: {}", e)
|
||
return ["谢谢分享！能再告诉我一些吗？"]
|
||
|
||
async def generate_profile_greeting(
|
||
self,
|
||
conversation_id: str,
|
||
missing_fields: List[str],
|
||
nickname: str = "",
|
||
) -> List[str]:
|
||
"""生成资料收集开场白，不持久化（由 Orchestrator 负责）"""
|
||
if not self.llm:
|
||
return ["你好！在开始之前，能告诉我你是哪一年出生的吗？"]
|
||
try:
|
||
prompt = get_profile_greeting_prompt(missing_fields, nickname)
|
||
hw = await get_history_with_window(
|
||
conversation_id,
|
||
max_pairs=settings.chat_history_max_pairs,
|
||
max_chars=settings.chat_history_max_chars,
|
||
)
|
||
messages: List[Any] = [SystemMessage(content=prompt)]
|
||
messages.extend(hw.window)
|
||
if hw.window:
|
||
messages.append(
|
||
HumanMessage(content="（请根据上文自然接话，继续资料收集开场。）")
|
||
)
|
||
else:
|
||
messages.append(HumanMessage(content="（请说出资料收集开场白。）"))
|
||
log_agent_payload(
|
||
logger,
|
||
"ProfileAgent.greeting.prompt",
|
||
format_history_string(
|
||
messages,
|
||
omit_system_body=settings.agent_log_omit_system_message_body,
|
||
),
|
||
)
|
||
prompt_chars = _message_contents_char_count(messages)
|
||
logger.info(
|
||
"event=chat_prompt_built agent=ProfileAgent.generate_profile_greeting "
|
||
"prompt_chars={} history_pairs_total={} history_pairs_windowed={}",
|
||
prompt_chars,
|
||
hw.turn_total,
|
||
len(hw.window) // 2,
|
||
)
|
||
response_text = await self._invoke_chat(
|
||
messages,
|
||
max_tokens=settings.chat_profile_followup_max_tokens,
|
||
conversation_id=conversation_id,
|
||
agent_name="ProfileAgent.generate_profile_greeting",
|
||
)
|
||
segments = await self._segments_from_response(
|
||
response_text,
|
||
max_segments=2,
|
||
max_chars_per_segment=settings.chat_interview_max_chars_per_segment,
|
||
fallback="你好！在开始之前，能告诉我你是哪一年出生的吗？",
|
||
)
|
||
log_agent_summary(
|
||
logger,
|
||
"ProfileAgent.greeting segments={} conversation_id={}",
|
||
len(segments),
|
||
conversation_id,
|
||
)
|
||
return segments
|
||
except Exception as e:
|
||
logger.error("生成资料收集开场白失败: {}", e)
|
||
return [
|
||
"你好！在我们开始聊人生故事之前，能先简单介绍一下你自己吗？比如你是哪一年出生的？"
|
||
]
|