forum_reader.py
4.84 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
"""
Forum日志读取工具
用于读取forum.log中的最新HOST发言
"""
import re
from pathlib import Path
from typing import Optional, List, Dict
from loguru import logger
from utils.runtime_paths import LOGS_DIR
DEFAULT_LOG_DIR = str(LOGS_DIR)
def get_latest_host_speech(log_dir: str = DEFAULT_LOG_DIR) -> Optional[str]:
"""
获取forum.log中最新的HOST发言
Args:
log_dir: 日志目录路径
Returns:
最新的HOST发言内容，如果没有则返回None
"""
try:
forum_log_path = Path(log_dir) / "forum.log"
if not forum_log_path.exists():
logger.debug("forum.log文件不存在")
return None
with open(forum_log_path, 'r', encoding='utf-8', errors='ignore') as f:
lines = f.readlines()
# 从后往前查找最新的HOST发言
host_speech = None
for line in reversed(lines):
# 匹配格式: [时间] [HOST] 内容
match = re.match(r'\[(\d{2}:\d{2}:\d{2})\]\s*\[HOST\]\s*(.+)', line)
if match:
_, content = match.groups()
# 处理转义的换行符，还原为实际换行
host_speech = content.replace('\\n', '\n').strip()
break
if host_speech:
logger.info(f"找到最新的HOST发言，长度: {len(host_speech)}字符")
else:
logger.debug("未找到HOST发言")
return host_speech
except Exception as e:
logger.error(f"读取forum.log失败: {str(e)}")
return None
def get_all_host_speeches(log_dir: str = DEFAULT_LOG_DIR) -> List[Dict[str, str]]:
"""
获取forum.log中所有的HOST发言
Args:
log_dir: 日志目录路径
Returns:
包含所有HOST发言的列表，每个元素是包含timestamp和content的字典
"""
try:
forum_log_path = Path(log_dir) / "forum.log"
if not forum_log_path.exists():
logger.debug("forum.log文件不存在")
return []
with open(forum_log_path, 'r', encoding='utf-8', errors='ignore') as f:
lines = f.readlines()
host_speeches = []
for line in lines:
# 匹配格式: [时间] [HOST] 内容
match = re.match(r'\[(\d{2}:\d{2}:\d{2})\]\s*\[HOST\]\s*(.+)', line)
if match:
timestamp, content = match.groups()
# 处理转义的换行符
content = content.replace('\\n', '\n').strip()
host_speeches.append({
'timestamp': timestamp,
'content': content
})
logger.info(f"找到{len(host_speeches)}条HOST发言")
return host_speeches
except Exception as e:
logger.error(f"读取forum.log失败: {str(e)}")
return []
def get_recent_agent_speeches(log_dir: str = DEFAULT_LOG_DIR, limit: int = 5) -> List[Dict[str, str]]:
"""
获取forum.log中最近的Agent发言（不包括HOST）
Args:
log_dir: 日志目录路径
limit: 返回的最大发言数量
Returns:
包含最近Agent发言的列表
"""
try:
forum_log_path = Path(log_dir) / "forum.log"
if not forum_log_path.exists():
return []
with open(forum_log_path, 'r', encoding='utf-8', errors='ignore') as f:
lines = f.readlines()
agent_speeches = []
for line in reversed(lines): # 从后往前读取
# 匹配格式: [时间] [AGENT_NAME] 内容
match = re.match(r'\[(\d{2}:\d{2}:\d{2})\]\s*\[(INSIGHT|MEDIA|QUERY)\]\s*(.+)', line)
if match:
timestamp, agent, content = match.groups()
# 处理转义的换行符
content = content.replace('\\n', '\n').strip()
agent_speeches.append({
'timestamp': timestamp,
'agent': agent,
'content': content
})
if len(agent_speeches) >= limit:
break
agent_speeches.reverse() # 恢复时间顺序
return agent_speeches
except Exception as e:
logger.error(f"读取forum.log失败: {str(e)}")
return []
def format_host_speech_for_prompt(host_speech: str) -> str:
"""
格式化HOST发言，用于添加到prompt中
Args:
host_speech: HOST发言内容
Returns:
格式化后的内容
"""
if not host_speech:
return ""
return f"""
### 论坛主持人最新总结
以下是论坛主持人对各Agent讨论的最新总结和引导，请参考其中的观点和建议：
{host_speech}
---
"""