e4bf0710c7
数据库 - 新增迁移 0003：timeline_events.memory_source_id 外键 → memory_sources，便于按 ingest 源做时间线幂等 后端 - 记忆 - 新增 ingest 后 LLM 富化（摘要/事实/时间线），可配置开关与最大字符数 - 新增证据包组装：合并 chunk、摘要、事实、时间线、故事等检索结果；支持空 query 时是否仍带 rolling 等开关 - repo/retriever/service/router/schemas/summarizer/timeline/extractor 等扩展；文档 memory-retrieval.md 更新 后端 - 对话 WS - 增加 PING/PONG；分段 ASR 日志与空音频处理；转写失败与「无助手回复」错误提示更明确 - 助手多段回复持久化使用统一分隔符，与分段逻辑一致 后端 - Agent - reply_limits：按 [SPLIT] 与段落拆段，并保证非空 fallback，供 WS 与 TTS 多段下发 后端 - 回忆录任务 - transcript ingest 记录 source_id；任务成功结?
235 lines
9.0 KiB
Python
235 lines
9.0 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 json
|
||
from typing import Any, Dict, List, Optional
|
||
|
||
from langchain_core.messages import AIMessage, HumanMessage
|
||
|
||
from app.agents.chat.helpers import format_history_string, get_history_messages
|
||
from app.agents.chat.prompts_profile import (
|
||
get_profile_extraction_prompt,
|
||
get_profile_followup_prompt,
|
||
get_profile_greeting_prompt,
|
||
)
|
||
from app.core.dependencies import get_llm_provider
|
||
from app.core.langchain_llm import ainvoke_json_object
|
||
from app.core.agent_logging import agent_span, log_agent_payload, log_agent_summary
|
||
from app.core.config import settings
|
||
from app.core.logging import get_logger
|
||
from app.agents.chat.reply_limits import (
|
||
nonempty_segments_or_fallback,
|
||
segments_from_llm_response,
|
||
truncate_chat_segments,
|
||
)
|
||
from app.features.memoir.memoir_images.json_payload import extract_json_payload
|
||
|
||
logger = get_logger(__name__)
|
||
|
||
|
||
def _get_langchain_llm():
|
||
try:
|
||
provider = get_llm_provider()
|
||
return getattr(provider, "langchain_llm", None)
|
||
except Exception:
|
||
return None
|
||
|
||
|
||
class ProfileAgent:
|
||
"""用户资料收集 Specialist Agent"""
|
||
|
||
def __init__(self):
|
||
self.llm = _get_langchain_llm()
|
||
|
||
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:
|
||
history_messages = await get_history_messages(conversation_id)
|
||
recent = (
|
||
history_messages[-4:] if len(history_messages) > 4 else history_messages
|
||
)
|
||
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
|
||
)
|
||
content = await ainvoke_json_object(
|
||
self.llm,
|
||
prompt,
|
||
max_tokens=512,
|
||
agent="ProfileAgent.extract_profile_from_message",
|
||
)
|
||
parsed = json.loads(extract_json_payload(content))
|
||
result = {}
|
||
if "birth_year" in parsed and 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 "birth_place" in parsed and parsed["birth_place"]:
|
||
result["birth_place"] = str(parsed["birth_place"])
|
||
if "grew_up_place" in parsed and parsed["grew_up_place"]:
|
||
result["grew_up_place"] = str(parsed["grew_up_place"])
|
||
if "occupation" in parsed and parsed["occupation"]:
|
||
result["occupation"] = str(parsed["occupation"])
|
||
return result
|
||
except (json.JSONDecodeError, 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,
|
||
user_message,
|
||
nickname,
|
||
interview_stage_hint=interview_stage_hint,
|
||
)
|
||
history_messages = await get_history_messages(conversation_id)
|
||
history_string = format_history_string(history_messages)
|
||
full_prompt = (
|
||
f"{prompt}\n\n{history_string}\n\nHuman: {user_message}\n\nAssistant:"
|
||
)
|
||
log_agent_payload(logger, "ProfileAgent.followup.prompt", full_prompt)
|
||
chat_llm = self.llm.bind(
|
||
max_tokens=settings.chat_profile_followup_max_tokens
|
||
)
|
||
with agent_span(
|
||
logger,
|
||
"ProfileAgent.followup.llm",
|
||
conversation_id=conversation_id,
|
||
):
|
||
response = await chat_llm.ainvoke(full_prompt)
|
||
response_text = (
|
||
response.content if hasattr(response, "content") else str(response)
|
||
)
|
||
log_agent_payload(
|
||
logger, "ProfileAgent.followup.raw_response", response_text
|
||
)
|
||
raw_list = segments_from_llm_response(response_text, max_segments=3)
|
||
if not raw_list:
|
||
raw_list = [response_text.strip()]
|
||
out = truncate_chat_segments(
|
||
raw_list,
|
||
max_segments=3,
|
||
max_chars_per_segment=settings.chat_interview_max_chars_per_segment,
|
||
)
|
||
log_agent_summary(
|
||
logger,
|
||
"ProfileAgent.followup segments={} conversation_id={}",
|
||
len(out),
|
||
conversation_id,
|
||
)
|
||
segments = (
|
||
out
|
||
if out
|
||
else [
|
||
response_text.strip()[
|
||
: settings.chat_interview_max_chars_per_segment
|
||
]
|
||
]
|
||
)
|
||
return nonempty_segments_or_fallback(
|
||
segments,
|
||
fallback="谢谢分享！能再告诉我一些吗？",
|
||
)
|
||
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)
|
||
history_messages = await get_history_messages(conversation_id)
|
||
history_string = format_history_string(history_messages)
|
||
full_prompt = f"{prompt}\n\n{history_string}" if history_string else prompt
|
||
log_agent_payload(logger, "ProfileAgent.greeting.prompt", full_prompt)
|
||
chat_llm = self.llm.bind(
|
||
max_tokens=settings.chat_profile_followup_max_tokens
|
||
)
|
||
with agent_span(
|
||
logger,
|
||
"ProfileAgent.greeting.llm",
|
||
conversation_id=conversation_id,
|
||
):
|
||
response = await chat_llm.ainvoke(full_prompt)
|
||
response_text = (
|
||
response.content if hasattr(response, "content") else str(response)
|
||
)
|
||
log_agent_payload(
|
||
logger, "ProfileAgent.greeting.raw_response", response_text
|
||
)
|
||
raw_list = segments_from_llm_response(response_text, max_segments=2)
|
||
if not raw_list:
|
||
raw_list = [response_text.strip()]
|
||
out = truncate_chat_segments(
|
||
raw_list,
|
||
max_segments=2,
|
||
max_chars_per_segment=settings.chat_interview_max_chars_per_segment,
|
||
)
|
||
log_agent_summary(
|
||
logger,
|
||
"ProfileAgent.greeting segments={} conversation_id={}",
|
||
len(out),
|
||
conversation_id,
|
||
)
|
||
segments = (
|
||
out
|
||
if out
|
||
else [
|
||
response_text.strip()[
|
||
: settings.chat_interview_max_chars_per_segment
|
||
]
|
||
]
|
||
)
|
||
return nonempty_segments_or_fallback(
|
||
segments,
|
||
fallback="你好！在开始之前，能告诉我你是哪一年出生的吗？",
|
||
)
|
||
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？"
|
||
]
|