三层回退恢复机制(L0写前留档/L1恢复梯子/L2离线回滚)+ guard 父守护

- L0: files 插件写受保护系统路径(/etc 等)前自动留档,AbstractBeforeWrite 到 data/file_baseline
- L1: failback 受限 worker 执行恢复梯子 probe→还原DNS/proxy→还原LLM配置+ReloadFromConfig→probe,N轮有界
- L2: tracker changeset 持久化原文 blob,guard 离线 RollbackFromDisk 回滚 agentfs;SystemSnapshot 支撑
- guard 父守护: 心跳 IPC(PING/ACK unix socket, 文件心跳回退)、失败计数、退出码协议(42/43/44)、最后手段
- 发行版路径适配: system.protected_paths/network_paths 可注入,默认面向主流 Linux
- Windows 兼容: guard.go/failback.go 加 //go:build linux, guard_windows.go 提供 no-op 桩
- 修复: guard.yaml last_resort 键冲突、changeset Content 不落盘导致离线回滚丢原文

Build 全绿, vet 干净, system/recovery/ipc/tracker 单元测试全过
This commit is contained in:
root
2026-08-05 16:00:08 +08:00
parent 33e97f2a99
commit bc9ef15eb0
28 changed files with 3675 additions and 167 deletions

View File

@ -26,46 +26,47 @@ type AgentID string
type SnapshotID string
type Snapshot struct {
ID SnapshotID `json:"id"`
AgentID AgentID `json:"agent_id"`
CreatedAt time.Time `json:"created_at"`
Reason string `json:"reason"`
Size int64 `json:"size_bytes"`
DockerImage string `json:"docker_image,omitempty"`
Valid bool `json:"valid"`
ID SnapshotID `json:"id"`
AgentID AgentID `json:"agent_id"`
CreatedAt time.Time `json:"created_at"`
Reason string `json:"reason"`
Size int64 `json:"size_bytes"`
DockerImage string `json:"docker_image,omitempty"`
Valid bool `json:"valid"`
}
type Heartbeat struct {
AgentID AgentID `json:"agent_id"`
Timestamp time.Time `json:"timestamp"`
State AgentState `json:"state"`
Health HealthStatus `json:"health"`
AgentID AgentID `json:"agent_id"`
Timestamp time.Time `json:"timestamp"`
State AgentState `json:"state"`
Health HealthStatus `json:"health"`
Uptime time.Duration `json:"uptime"`
LLMConnected bool `json:"llm_connected"`
Error string `json:"error,omitempty"`
LLMConnected bool `json:"llm_connected"`
Error string `json:"error,omitempty"`
}
type NetworkCheckResult struct {
LLMAPIReachable bool `json:"llm_api_reachable"`
DNSResolving bool `json:"dns_resolving"`
TCPReachable bool `json:"tcp_reachable"`
Latency time.Duration `json:"latency_ms"`
LatencyDegraded bool `json:"latency_degraded"`
Error string `json:"error,omitempty"`
LLMAPIReachable bool `json:"llm_api_reachable"`
EndpointsConfigured bool `json:"endpoints_configured"`
DNSResolving bool `json:"dns_resolving"`
TCPReachable bool `json:"tcp_reachable"`
Latency time.Duration `json:"latency_ms"`
LatencyDegraded bool `json:"latency_degraded"`
Error string `json:"error,omitempty"`
}
type SnapshotPolicy struct {
Interval time.Duration `json:"interval"`
MaxSnapshots int `json:"max_snapshots"`
PreAction bool `json:"pre_action"`
PostAction bool `json:"post_action"`
Interval time.Duration `json:"interval"`
MaxSnapshots int `json:"max_snapshots"`
PreAction bool `json:"pre_action"`
PostAction bool `json:"post_action"`
}
type RollbackPolicy struct {
MaxRetries int `json:"max_retries"`
HealthThreshold HealthStatus `json:"health_threshold"`
CooldownPeriod time.Duration `json:"cooldown_period"`
AutoRollback bool `json:"auto_rollback"`
MaxRetries int `json:"max_retries"`
HealthThreshold HealthStatus `json:"health_threshold"`
CooldownPeriod time.Duration `json:"cooldown_period"`
AutoRollback bool `json:"auto_rollback"`
}
type AgentConfig struct {
@ -87,12 +88,12 @@ type ResourceLimit struct {
}
type OperationLog struct {
ID string `json:"id"`
AgentID AgentID `json:"agent_id"`
Timestamp time.Time `json:"timestamp"`
Action string `json:"action"`
ID string `json:"id"`
AgentID AgentID `json:"agent_id"`
Timestamp time.Time `json:"timestamp"`
Action string `json:"action"`
SnapshotID SnapshotID `json:"snapshot_id,omitempty"`
Success bool `json:"success"`
Success bool `json:"success"`
}
type LLMSource struct {