agent-Specialization/server/utils_common.py
JOJO eaa5e3bee9 refactor(runtime): 运行态数据迁出源码树到 ~/.agents,日志默认关并加轮转,清理实验残留
将运行态数据(对话/用户工作区/日志等)默认迁出源码树到 ~/.agents/<mode>,
对齐 ~/.claude、~/.codex 惯例;同时为日志加上开关与轮转,并归档/清理仓库内
长期堆积的实验残留与误产生文件。

## 路径变量重写(核心)
- 重写 config/paths.py:运行态根按模式分流,host -> ~/.agents/host,
  其它(默认 docker/web)-> ~/.agents/web。
- 三级解析优先级(高→低):
  1) 具体目录变量 DATA_DIR / LOGS_DIR / USER_SPACE_DIR / API_USER_SPACE_DIR
  2) 模式根变量 AGENTS_HOST_HOME / AGENTS_WEB_HOME
  3) 兜底 ~/.agents/<mode>
- 导出变量名保持不变,20+ 处消费方零改动;统一 config/sub_agent.py 重复的
  路径解析逻辑,将 sub_agent 任务目录/状态文件收编进 DATA_DIR;
  SUB_AGENT_PROJECT_RESULTS_DIR 仍随工作区(有意保留)。
- config/*.json、prompts/、agentskills/ 属配置/资源,仍锚定源码树。

## 日志止血
- 新增 utils/log_rotation.py:按大小轮转(默认 20MB×3 份)+ 按份清理
  (dump 默认保留最近 30 个),阈值可由 AGENT_LOG_ROTATE_MAX_BYTES /
  AGENT_LOG_ROTATE_BACKUPS / AGENT_DUMP_KEEP 覆盖。
- utils/api_client.py:API 请求体 dump 默认关闭(AGENT_API_DUMP_ENABLED 开启),
  收编两处写死的 logs/ 硬编码路径改用 LOGS_DIR;dump 关闭时 request_dump 安全置空。
- utils/host_workspace_debug.py、server/utils_common.py(chunk/conn_diag 等)、
  utils/logger.py(TaskLogger/ErrorLogger)统一接入轮转。

## 迁移与运维脚本
- scripts/migrate_runtime_data.py:源码树 -> 运行态根,复制+备份+校验+可回滚+幂等,
  logs 丢弃不迁;import config 复用程序同一套路径解析(模式由 .env 决定),
  覆盖 data/users/api 及 sub_agent/tasks(-> data/sub_agent_tasks)。
- scripts/cleanup_misplaced_web.sh:清理误迁到 ~/.agents/web 的副本(带 chflags 兜底)。

## 测试
- 重写 test/test_config_paths_resolution.py:覆盖默认分流、模式切换、模式根变量覆盖、
  具体目录变量最高优先级、相对路径锚定 repo root、源码树配置项不随迁移等 6 个用例。

## 仓库清理
- 删除旧版子智能体目录 sub_agent/(逻辑已统一在 easyagent/)。
- 删除误产生/垃圾文件:误敲命令生成的 "ystemctl status ..."、空文件 .zhouyanbo /
  testfile_from_ai、运行态日志/pid、test_playwright.png、test_system_message.py 等。
- 实验残留与历史文档(BUG_FIX/POLLING 变更日志、SUB_AGENT 文档、翻译资料、
  model_tests、compact_result、奇奇怪怪的bug、截图、goal_research)归档到
  本地 _experiments/,并从版本控制移除(已加入 .gitignore)。
- .gitignore:新增 api/、_experiments/,清理已失效的 sub_agent/* 条目与冗余项。

## 文档
- CLAUDE.md / AGENTS.md:补充数据目录与路径变量、日志策略、迁移流程,
  更新目录结构(移除 sub_agent、新增 _experiments/scripts),调试日志路径改为 ~/.agents/<mode>/logs/。
2026-06-01 13:17:32 +08:00

203 lines
7.4 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

"""通用工具:文本处理、日志写入等(由原 web_server.py 拆分)。"""
from __future__ import annotations
import json
import logging
from datetime import datetime
from pathlib import Path
from typing import Any, Dict, List
from config import LOGS_DIR
from utils.log_rotation import append_line as _append_rotating
# 文件名安全处理
def _sanitize_filename_component(text: str) -> str:
safe = (text or "untitled").strip()
safe = __import__('re').sub(r'[\\/:*?"<>|]+', '_', safe)
return safe or "untitled"
def build_review_lines(messages, limit=None):
"""
将对话消息序列拍平成简化文本。
保留 user / assistant / system 以及 assistant 内的 tool 调用与 tool 消息。
limit 为正整数时,最多返回该数量的行(用于预览)。
"""
lines: List[str] = []
def append_line(text: str):
lines.append(text.rstrip())
def extract_text(content):
if isinstance(content, str):
return content
if isinstance(content, list):
parts = []
for item in content:
if isinstance(item, dict) and item.get("type") == "text":
parts.append(item.get("text") or "")
elif isinstance(item, str):
parts.append(item)
return "".join(parts)
if isinstance(content, dict):
return content.get("text") or ""
return ""
def append_tool_call(name, args):
try:
args_text = json.dumps(args, ensure_ascii=False)
except Exception:
args_text = str(args)
append_line(f"tool_call{name} {args_text}")
for msg in messages or []:
role = msg.get("role")
base_content_raw = msg.get("content") if isinstance(msg.get("content"), (str, list, dict)) else msg.get("text") or ""
base_content = extract_text(base_content_raw)
if role in ("user", "assistant", "system"):
append_line(f"{role}{base_content}")
if role == "tool":
append_line(f"tool{extract_text(base_content_raw)}")
if role == "assistant":
actions = msg.get("actions") or []
for action in actions:
if action.get("type") != "tool":
continue
tool = action.get("tool") or {}
name = tool.get("name") or "tool"
args = tool.get("arguments")
if args is None:
args = tool.get("argumentSnapshot")
try:
args_text = json.dumps(args, ensure_ascii=False)
except Exception:
args_text = str(args)
append_line(f"tool_call{name} {args_text}")
tool_content = tool.get("content")
if tool_content is None:
if isinstance(tool.get("result"), str):
tool_content = tool.get("result")
elif tool.get("result") is not None:
try:
tool_content = json.dumps(tool.get("result"), ensure_ascii=False)
except Exception:
tool_content = str(tool.get("result"))
elif tool.get("message"):
tool_content = tool.get("message")
else:
tool_content = ""
append_line(f"tool{tool_content}")
if isinstance(limit, int) and limit > 0 and len(lines) >= limit:
return lines[:limit]
tool_calls = msg.get("tool_calls") or []
for tc in tool_calls:
fn = tc.get("function") or {}
name = fn.get("name") or "tool"
args_raw = fn.get("arguments")
try:
args_obj = json.loads(args_raw) if isinstance(args_raw, str) else args_raw
except Exception:
args_obj = args_raw
append_tool_call(name, args_obj)
if isinstance(limit, int) and limit > 0 and len(lines) >= limit:
return lines[:limit]
if isinstance(base_content_raw, list):
for item in base_content_raw:
if isinstance(item, dict) and item.get("type") == "tool_call":
fn = item.get("function") or {}
name = fn.get("name") or "tool"
args_raw = fn.get("arguments")
try:
args_obj = json.loads(args_raw) if isinstance(args_raw, str) else args_raw
except Exception:
args_obj = args_raw
append_tool_call(name, args_obj)
if isinstance(limit, int) and limit > 0 and len(lines) >= limit:
return lines[:limit]
if isinstance(limit, int) and limit > 0 and len(lines) >= limit:
return lines[:limit]
return lines if limit is None else lines[:limit]
# 日志输出
_ORIGINAL_PRINT = print
ENABLE_VERBOSE_CONSOLE = True
def brief_log(message: str):
"""始终输出的简要日志(模型输出/工具调用等关键事件)"""
try:
_ORIGINAL_PRINT(message)
except Exception:
pass
DEBUG_LOG_FILE = Path(LOGS_DIR).expanduser().resolve() / "debug_stream.log"
CHUNK_BACKEND_LOG_FILE = Path(LOGS_DIR).expanduser().resolve() / "chunk_backend.log"
CHUNK_FRONTEND_LOG_FILE = Path(LOGS_DIR).expanduser().resolve() / "chunk_frontend.log"
STREAMING_DEBUG_LOG_FILE = Path(LOGS_DIR).expanduser().resolve() / "streaming_debug.log"
CONN_DIAG_LOG_FILE = Path(LOGS_DIR).expanduser().resolve() / "conn_diag.log"
def _write_log(file_path: Path, message: str) -> None:
timestamp = datetime.now().strftime('%Y-%m-%d %H:%M:%S.%f')[:-3]
_append_rotating(file_path, f"[{timestamp}] {message}")
def debug_log(message):
"""写入调试日志"""
_write_log(DEBUG_LOG_FILE, message)
def log_conn_diag(message: str):
"""连接诊断日志:统一关键词并直接落盘到独立文件。"""
_write_log(CONN_DIAG_LOG_FILE, f"[CONN_DIAG] {message}")
def log_backend_chunk(conversation_id: str, iteration: int, chunk_index: int, elapsed: float, char_len: int, content_preview: str):
preview = content_preview.replace('\n', '\\n')
_write_log(
CHUNK_BACKEND_LOG_FILE,
f"conv={conversation_id or 'unknown'} iter={iteration} chunk={chunk_index} elapsed={elapsed:.3f}s len={char_len} preview={preview}"
)
def log_frontend_chunk(conversation_id: str, chunk_index: int, elapsed: float, char_len: int, client_ts: float):
_write_log(
CHUNK_FRONTEND_LOG_FILE,
f"conv={conversation_id or 'unknown'} chunk={chunk_index} elapsed={elapsed:.3f}s len={char_len} client_ts={client_ts}"
)
def log_streaming_debug_entry(data: Dict[str, Any]):
try:
serialized = json.dumps(data, ensure_ascii=False)
except Exception:
serialized = str(data)
_write_log(STREAMING_DEBUG_LOG_FILE, serialized)
__all__ = [
"_sanitize_filename_component",
"build_review_lines",
"brief_log",
"debug_log",
"log_backend_chunk",
"log_frontend_chunk",
"log_streaming_debug_entry",
"DEBUG_LOG_FILE",
"CHUNK_BACKEND_LOG_FILE",
"CHUNK_FRONTEND_LOG_FILE",
"STREAMING_DEBUG_LOG_FILE",
"CONN_DIAG_LOG_FILE",
"log_conn_diag",
]