"""Cloud Hypervisor 执行器配置解析(叶子模块,不依赖 cloud.sandbox,避免循环导入)。 职责只有两件:内存字符串解析,以及把构造参数 + 环境变量 解析成一份显式配置。参数优先于环境变量、环境变量优先于 默认值——与 #216 原 __init__ 的 `or` 链完全一致,只收紧了 两处原来会静默 fallback 的 nonsense 输入(见下文),收紧点 在 PR 描述里明写、单测钉住: - CHV_SSH_USER 显式传空字符串:原来 `or` 链会静默 fallback 成 root(调用方以为没给用户、实际跑了 root),现在直接 ValueError。 - CHV_SSH_PORT 显式传 0、或解析后超出 1-65535:原来 0 会 静默 fallback 成 2222、其它越界值会原样进 ssh 命令,现在 直接 ValueError。 与 #215 的关系(只列清单,不复制模块):#215 未合并, 本轨不假装复用它。#215 合并后应再复用的点:超时类 (api_timeout/ready_timeout/ready_interval/task_timeout → timeouts 模块)、门禁类(preflight fail-fast、容量门、磁盘 配额门、egress fail-closed → gates 模块)、配额类 (max_vms、disk_gb、任务成本走 worker quota → quota 模块)、 隔离类(单任务单 VM、磁盘 copy 模式、egress 代理、SSH 钉死 → sandbox_policy 模块)。见 PR 描述的复用清单。 """ import os import re def _parse_memory_bytes(value): """内存字符串转字节:2G/512M/1024K/2048(无单位=字节)。 非法值 ValueError,绝不静默按默认算。""" m = re.match(r"^\s*(\d+)\s*([KMGkmg]?)\s*[Bb]?\s*$", str(value)) if not m: raise ValueError("CHV_MEM 格式非法:%r" % (value,)) mult = {"": 1, "K": 1024, "M": 1024 ** 2, "G": 1024 ** 3} return int(m.group(1)) * mult[m.group(2).upper()] class ChvConfig: """解析后的 CHV 配置:纯数据对象,字段名与 CloudHypervisorExecutor 原 __init__ 的属性名一一对应, 执行器 __init__ 直接把字段抄到 self 上,旧测试读属性 的方式全部不变。""" def __init__(self, **fields): for key, value in fields.items(): setattr(self, key, value) def _ssh_fragment(params: dict, env: dict) -> dict: """SSH/命令面配置片段:返回 dict,供 build_chv_config 组装。 错误文案与原内联代码逐字一致,校验时机不变(构造时)。""" ssh_key = params.get("ssh_key") or env.get("CHV_SSH_KEY") if params.get("ssh_user") is not None \ and params.get("ssh_user") == "": raise ValueError("CHV_SSH_USER 不能为空字符串") ssh_user = params.get("ssh_user") or env.get("CHV_SSH_USER") \ or "root" if params.get("ssh_port") is not None: raw_port = params.get("ssh_port") else: raw_port = env.get("CHV_SSH_PORT") or 2222 try: ssh_port = int(raw_port) except (TypeError, ValueError): raise ValueError("CHV_SSH_PORT 必须是整数") if not 1 <= ssh_port <= 65535: raise ValueError("CHV_SSH_PORT 必须在 1-65535 之间") host_key_mode = params.get("host_key_mode") \ or env.get("CHV_HOST_KEY_MODE") or "provisioned" if host_key_mode not in ("provisioned", "keyscan"): raise ValueError( "CHV_HOST_KEY_MODE 只能是 provisioned 或 keyscan:%s" % host_key_mode) return { "ssh_key": ssh_key, "ssh_user": ssh_user, "ssh_port": ssh_port, "host_key_mode": host_key_mode, "guest_host_py": params.get("guest_host_py") or "/app/host.py", "cmdline": params.get("cmdline") or env.get("CHV_CMDLINE") or "console=hvc0 root=/dev/vda1 rw", "net": params.get("net") or env.get("CHV_NET"), "net_json": params.get("net_json") or env.get("CHV_NET_JSON"), "ssh_host": params.get("ssh_host") or env.get("CHV_SSH_HOST"), "ssh_forward": env.get("CHV_SSH_FORWARD") == "1", } def _quota_fragment(env: dict) -> dict: """配额/磁盘/快照配置片段:返回 dict,错误文案逐字一致。""" try: max_vms = int(env.get("CHV_MAX_VMS") or 4) except ValueError: raise ValueError("CHV_MAX_VMS 必须是整数") disk_mode = env.get("CHV_DISK_MODE") or "copy" if disk_mode not in ("copy", "reuse"): raise ValueError( "CHV_DISK_MODE 只能是 copy 或 reuse:%s" % disk_mode) try: disk_gb = float(env.get("CHV_DISK_GB")) \ if env.get("CHV_DISK_GB") else 50.0 except ValueError: raise ValueError("CHV_DISK_GB 必须是数字") if disk_gb <= 0: raise ValueError("CHV_DISK_GB 必须大于 0") try: snapshot_max_count = int(env.get("CHV_SNAPSHOT_MAX_COUNT") or 10) snapshot_max_total_gb = float( env.get("CHV_SNAPSHOT_MAX_TOTAL_GB") or 20.0) snapshot_retention_days = float( env.get("CHV_SNAPSHOT_RETENTION_DAYS") or 30.0) except ValueError: raise ValueError("CHV_SNAPSHOT_* 必须是数字") if snapshot_max_count < 0 or snapshot_max_total_gb < 0 \ or snapshot_retention_days < 0: raise ValueError("CHV_SNAPSHOT_* 不能为负数") return { "max_vms": max_vms, "disk_mode": disk_mode, "disk_gb": disk_gb, "reuse_experiment": env.get( "CHV_REUSE_SINGLE_TENANT_EXPERIMENT") == "1", "single_tenant_project": env.get("CHV_SINGLE_TENANT_PROJECT"), "snapshot_max_count": snapshot_max_count, "snapshot_max_total_gb": snapshot_max_total_gb, "snapshot_retention_days": snapshot_retention_days, "snapshot_dir": env.get("CHV_SNAPSHOT_DIR"), "allow_remote_snapshot": env.get("CHV_ALLOW_REMOTE_SNAPSHOT") == "1", "egress_proxy": env.get("CHV_EGRESS_PROXY"), "allow_direct_egress": env.get("CHV_ALLOW_DIRECT_EGRESS") == "1", } def _timeout_fragment(params: dict, env: dict) -> dict: """超时/池/快照 URL 配置片段:返回 dict,错误文案逐字一致。""" task_timeout_raw = env.get("CHV_TASK_TIMEOUT") task_timeout = float(task_timeout_raw) \ if task_timeout_raw else None try: warm_pool_size = int(env.get("CHV_WARM_POOL_SIZE") or 0) except ValueError: raise ValueError("CHV_WARM_POOL_SIZE 必须是整数") try: api_timeout = float( params.get("api_timeout") if params.get("api_timeout") is not None else env.get("CHV_API_TIMEOUT") or 30) ready_timeout = float( params.get("ready_timeout") if params.get("ready_timeout") is not None else env.get("CHV_READY_TIMEOUT") or 120) ready_interval = float( params.get("ready_interval") if params.get("ready_interval") is not None else env.get("CHV_READY_INTERVAL") or 5) except ValueError: raise ValueError("CHV_*_TIMEOUT/INTERVAL 必须是数字") if ready_interval <= 0: ready_interval = 5 return { "task_timeout": task_timeout, "warm_pool_size": warm_pool_size, "api_timeout": api_timeout, "ready_timeout": ready_timeout, "ready_interval": ready_interval, "snapshot_url": env.get("CHV_SNAPSHOT_URL"), } def _assemble_chv_config(base: dict, ssh: dict, quota: dict, timeouts: dict): """把基础字段 + SSH/配额/超时三个片段组装成 ChvConfig。 纯移动:字段名与取值逐字不变,build_chv_config 只解析。""" return ChvConfig( binary=base["binary"], kernel=base["kernel"], rootfs=base["rootfs"], cpus=base["cpus"], memory=base["memory"], state_dir=base["state_dir"], ssh_key=ssh["ssh_key"], ssh_user=ssh["ssh_user"], ssh_port=ssh["ssh_port"], guest_host_py=ssh["guest_host_py"], cmdline=ssh["cmdline"], net=ssh["net"], net_json=ssh["net_json"], kvm_path=base["kvm_path"], cpuinfo_path=base["cpuinfo_path"], ch_remote=base["ch_remote"], model=base["model"], max_vms=quota["max_vms"], disk_mode=quota["disk_mode"], disk_gb=quota["disk_gb"], ssh_host=ssh["ssh_host"], ssh_forward=ssh["ssh_forward"], reuse_experiment=quota["reuse_experiment"], egress_proxy=quota["egress_proxy"], allow_direct_egress=quota["allow_direct_egress"], host_key_mode=ssh["host_key_mode"], task_timeout=timeouts["task_timeout"], snapshot_url=timeouts["snapshot_url"], warm_pool_size=timeouts["warm_pool_size"], api_timeout=timeouts["api_timeout"], ready_timeout=timeouts["ready_timeout"], ready_interval=timeouts["ready_interval"], single_tenant_project=quota["single_tenant_project"], snapshot_max_count=quota["snapshot_max_count"], snapshot_max_total_gb=quota["snapshot_max_total_gb"], snapshot_retention_days=quota["snapshot_retention_days"], snapshot_dir=quota["snapshot_dir"], allow_remote_snapshot=quota["allow_remote_snapshot"]) def build_chv_config(params: dict, env: dict): """把显式构造参数与环境变量解析成 ChvConfig(见 _assemble_chv_config 的组装段;片段化与校验顺序不变)。""" env = env if env is not None else {} base = { "binary": params.get("binary") or env.get("CHV_BINARY") or "cloud-hypervisor", "kernel": params.get("kernel") or env.get("CHV_KERNEL"), "rootfs": params.get("rootfs") or params.get("image") or env.get("CHV_ROOTFS") or env.get("CHV_IMAGE"), "cpus": str(params.get("cpus") or env.get("CHV_CPU") or "2"), "memory": params.get("memory") or env.get("CHV_MEM") or "2G", "state_dir": params.get("state_dir") or env.get("CHV_STATE_DIR") or os.path.join(os.path.expanduser("~"), ".local", "share", "codex-app-server", "chv-vms"), "kvm_path": params.get("kvm_path") if params.get("kvm_path") is not None else "/dev/kvm", "cpuinfo_path": params.get("cpuinfo_path") if params.get("cpuinfo_path") is not None else "/proc/cpuinfo", "ch_remote": params.get("ch_remote") or env.get("CHV_REMOTE") or "ch-remote", "model": params.get("model"), } return _assemble_chv_config( base, _ssh_fragment(params, env), _quota_fragment(env), _timeout_fragment(params, env))