feat(chv): 架构与代码质量提升——WarmPool 定案、长函数提取、严格测试替身、Docker 同步守卫、配置统一校验、类型注解与 ADR

堆叠于 #246(feat-chv-secfix),只到 PR OPEN,未合并、未部署。
安全语义不变:egress、key seed 投递、磁盘删除、默认 provisioned、
tap 校验一律保留;前端零改动。
- WarmPool 定案为实验性(ADR-5):dispatch 永远冷启动,
  wired_to_dispatch 恒 False,acquire/resume 只保留实验接口,
  worker 仍调 reconcile_orphans 清理残留。
- 长函数提取:preflight 126→31、wake_vm 135→36、__init__ 69→31、
  build_chv_config 159→58;错误文案逐字不变。
- 严格测试替身:fake API 校验 VmConfig(任务盘+seed 盘、net
  无重复),fake SSH 校验 known_hosts 钉死;新增 5 项测试。
- Docker 同步守卫:8 个真实标记用例下 Docker 内联版与正典
  parse_goal_result 状态全等,改分叉即 fail。
- 配置统一校验:preflight 以 config_invalid 统一兜底端口/配额/
  超时/快照/host-key 模式(构造时已校验正常值,preflight 兜底
  事后改写);CHV_NET 与 CHV_NET_JSON 双设仍警告不硬拒。
- 类型与 lint:chv 叶子模块公开 API 补类型注解;stdlib 扫描
  揪出 executor 内 1 个真死 import(host_key_paths)并删除。
- ADR:docs/chv-architecture.md(ADR-1 至 ADR-7)。
测试:CHV 163 项全过;cloud 全量 1593 项三跑结果为 8 errors
(首跑详细日志因 tail 截断丢失)、全过、1 失败(浏览器代理
时序测试,与 CHV 无关),全量本身存在时序偶发,CHV 套件
确定性全过。
This commit is contained in:
host committed 2026-10-31 05:50:56 +00:00
1 parent baf26beb78
commit c908a0147a
12 files changed
+725 -239

No files matched your search

+110 -91
View File
@@ -50,24 +50,10 @@ class ChvConfig:
setattr(self, key, value)
def build_chv_config(params, env):
"""把显式构造参数(params,None=未给)与环境变量(env,
默认为 os.environ 的调用方传入 dict)解析成 ChvConfig。
显式参数只有 __init__ 本来就有的那些;max_vms、磁盘模式、
磁盘配额、egress、快照、预热池目标数本来就没有显式参数,
仍只走环境变量(与 #216 一致,不悄悄加新参数面)。"""
env = env if env is not None else {}
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")
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") == "":
@@ -84,32 +70,27 @@ def build_chv_config(params, env):
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")
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")
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"
# P0-4 SSH 目标解析(feat-chv-fix):显式 CHV_SSH_HOST 优先;
# 其次取 VmConfig net 首个带 ip 的条目(静态 tap 客机 IP,
# 即选定的客机 IP 发现方案);两者皆无时只有显式
# CHV_SSH_FORWARD=1 才允许回环 127.0.0.1(运维宣称宿主
# NAT 已把该端口转发到客机 sshd),否则执行器在 wake/
# wait 时报 ssh_target_undeclared,绝不无条件假设回环能通。
# vsock 未选:需客内 agent + 宿主代理两套新代码(#216 已
# 否决);纯 NAT 方案未选:DNAT 是宿主防火墙外部状态,
# 执行器代码既不能创建也不能校验它,写进代码仍是假保证。
ssh_host = params.get("ssh_host") or env.get("CHV_SSH_HOST")
ssh_forward = env.get("CHV_SSH_FORWARD") == "1"
# P0-3:reuse 实验二次确认(名字即带实验含义)。
reuse_experiment = env.get(
"CHV_REUSE_SINGLE_TENANT_EXPERIMENT") == "1"
model = params.get("model")
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:
@@ -118,35 +99,13 @@ def build_chv_config(params, env):
if disk_mode not in ("copy", "reuse"):
raise ValueError(
"CHV_DISK_MODE 只能是 copy 或 reuse:%s" % disk_mode)
disk_gb_raw = env.get("CHV_DISK_GB")
# feat-chv-secfix(M3):配额默认开启。CHV_DISK_GB 未设时
# 不再是 None(配额门直接返回),而是 50 GB 总量预算;
# 显式设 0 或负数同样非法——配额门是 fail-closed,不是
# “设个小值绕过”。check_disk_quota 仍接受 None(直接
# 调用者的第二道门),但执行器路径永远带默认值。
try:
disk_gb = float(disk_gb_raw) if disk_gb_raw else 50.0
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")
egress_proxy = env.get("CHV_EGRESS_PROXY")
allow_direct_egress = env.get("CHV_ALLOW_DIRECT_EGRESS") == "1"
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)
# feat-chv-secfix(M6):reuse 实验放行须同时声明单租户
# 项目(部署声明 + 审计,代码无法从环境变量验证数据库
# 里是否真的只有一个租户——这一点在文档与 preflight 的
# kind 里明写,不假装已校验)。
single_tenant_project = env.get("CHV_SINGLE_TENANT_PROJECT")
# feat-chv-secfix(M3 快照上限 / L2 快照目录白名单):
# 快照数、总量、保留期均有默认值;file:// 快照只允许在
# state_dir 或 CHV_SNAPSHOT_DIR 内,远端协议须显式放行
# (见 hardening.validate_snapshot_url)。
try:
snapshot_max_count = int(env.get("CHV_SNAPSHOT_MAX_COUNT")
or 10)
@@ -159,13 +118,29 @@ def build_chv_config(params, env):
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")
snapshot_dir = env.get("CHV_SNAPSHOT_DIR")
allow_remote_snapshot = env.get("CHV_ALLOW_REMOTE_SNAPSHOT") \
== "1"
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
snapshot_url = env.get("CHV_SNAPSHOT_URL")
try:
warm_pool_size = int(env.get("CHV_WARM_POOL_SIZE") or 0)
except ValueError:
@@ -187,25 +162,69 @@ def build_chv_config(params, env):
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 build_chv_config(params: dict, env: dict):
"""把显式构造参数(params,None=未给)与环境变量(env,
默认为 os.environ 的调用方传入 dict)解析成 ChvConfig。
显式参数只有 __init__ 本来就有的那些;max_vms、磁盘模式、
磁盘配额、egress、快照、预热池目标数本来就没有显式参数,
仍只走环境变量(与 #216 一致,不悄悄加新参数面)。
片段化(feat-chv-arch95):SSH 面、配额面、超时面分别
由 _ssh_fragment/_quota_fragment/_timeout_fragment 解析,
错误文案与校验顺序逐字一致;build_chv_config 只组装。"""
env = env if env is not None else {}
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")
ssh = _ssh_fragment(params, env)
quota = _quota_fragment(env)
timeouts = _timeout_fragment(params, env)
return ChvConfig(
binary=binary, kernel=kernel, rootfs=rootfs, cpus=cpus,
memory=memory, state_dir=state_dir, ssh_key=ssh_key,
ssh_user=ssh_user, ssh_port=ssh_port,
guest_host_py=guest_host_py, cmdline=cmdline, net=net,
net_json=net_json, kvm_path=kvm_path,
cpuinfo_path=cpuinfo_path, ch_remote=ch_remote, model=model,
max_vms=max_vms, disk_mode=disk_mode, disk_gb=disk_gb,
ssh_host=ssh_host, ssh_forward=ssh_forward,
reuse_experiment=reuse_experiment,
egress_proxy=egress_proxy,
allow_direct_egress=allow_direct_egress,
host_key_mode=host_key_mode,
task_timeout=task_timeout, snapshot_url=snapshot_url,
warm_pool_size=warm_pool_size, api_timeout=api_timeout,
ready_timeout=ready_timeout, ready_interval=ready_interval,
single_tenant_project=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=snapshot_dir,
allow_remote_snapshot=allow_remote_snapshot)
memory=memory, state_dir=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=kvm_path, cpuinfo_path=cpuinfo_path,
ch_remote=ch_remote, model=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"])