Files
knowledge-governance/internal/monitoring/health_test.go
T
zheromiku dcdc8d1ddd feat: 知识治理平台(含已验证发布/回滚契约)
全栈知识治理平台首次入库(P1-P10 + 发布链路模拟验证闭环):

- 治理核心:源目录/变更集/人工审核/发布批次/发布执行(fail-closed 闸口)
- 测试通道:WeKnora 测试 KB 上传/轮询/验收;poll 完成时写入
  parser_generation/index_generation,修复 manual/seed 路径发布闸口永久拦截
- 发布适配器 v071(本地 source=测试角色 / 云端 target=生产角色 模拟验证通过):
  * ES 导出/导入 mapping 自适应(.keyword 子字段、可选 tenant_id)
  * OSS locator 支持嵌套 scheme;chunks.seq_id 由目标序列分配
  * bundle 归档同身份重试原子替换;verifier 按 bundle chunk_type 计数
  * 回滚 job payload 支持 prior_execution_id(strict 解码)
- 三通道发布+回滚演练实测:publish 4/4 verified,检索命中,
  rollback 4/4 rolled_back,目标端 PG is_enabled=false、ES is_enabled=false
- 前端 A·Data-console 风格全站统一,120 用例通过
- 门禁:go vet / go test 全包通过,gofmt 干净
2026-09-30 10:54:06 +08:00

85 lines
3.9 KiB
Go

package monitoring
import (
"context"
"errors"
"fmt"
"net"
"strings"
"testing"
"time"
)
func testNow() time.Time { return time.Date(2026, 9, 12, 9, 0, 0, 0, time.UTC) }
func TestClassifySeparatesNotApplicableNotConfiguredAndFailures(t *testing.T) {
now := testNow()
notDeployed := classify("redis", "Redis / MQ", false, false, ProbeOutcome{ObservedAt: now})
if notDeployed.Liveness != LiveUnknown || notDeployed.Readiness != ReadNotApplicable {
t.Fatalf("not deployed = %+v", notDeployed)
}
notConfigured := classify("mineru", "MinerU", false, true, ProbeOutcome{ObservedAt: now})
if notConfigured.Liveness != LiveUnknown || notConfigured.Readiness != ReadNotConfigured {
t.Fatalf("not configured = %+v", notConfigured)
}
healthy := classify("postgres", "PostgreSQL", true, true, ProbeOutcome{ObservedAt: now})
if healthy.Liveness != LiveUp || healthy.Readiness != ReadReady {
t.Fatalf("healthy = %+v", healthy)
}
// DNS failure: down + blocked with sanitized reason, never the raw host.
dns := &net.DNSError{Err: "no such host", Name: "weknora.internal.example"}
down := classify("weknora", "WeKnora", true, true, ProbeOutcome{ObservedAt: now, Reachability: dns})
if down.Liveness != LiveDown || down.Reason == "" || strings.Contains(down.Reason, "weknora.internal") {
t.Fatalf("dns down = %+v", down)
}
// Timeout.
timeout := classify("weknora", "WeKnora", true, true, ProbeOutcome{ObservedAt: now, Reachability: context.DeadlineExceeded})
if timeout.Liveness != LiveDown || timeout.Readiness != ReadBlocked {
t.Fatalf("timeout = %+v", timeout)
}
// Reachable but capacity full => live up, readiness blocked, distinct reason.
capacity := classify("mineru", "MinerU", true, true, ProbeOutcome{ObservedAt: now, Reachability: errCapacityFull})
if capacity.Liveness != LiveUp || capacity.Readiness != ReadBlocked || capacity.Reason == "" {
t.Fatalf("capacity = %+v", capacity)
}
// Reachable but permission denied on target KB (readiness error only).
perm := classify("weknora", "WeKnora", true, true, ProbeOutcome{ObservedAt: now, WorkReadiness: errNoPermission})
if perm.Liveness != LiveUp || perm.Readiness != ReadBlocked {
t.Fatalf("permission = %+v", perm)
}
}
func TestHealthTrackerRemembersSuccessAndFailStreak(t *testing.T) {
tracker := newHealthTracker()
now := testNow()
first := tracker.apply("postgres", classify("postgres", "PostgreSQL", true, true, ProbeOutcome{ObservedAt: now}))
if first.LastSuccessAt == nil || !first.LastSuccessAt.Equal(now) || first.ConsecutiveFailures != 0 {
t.Fatalf("first = %+v", first)
}
later := now.Add(time.Minute)
bad := tracker.apply("postgres", classify("postgres", "PostgreSQL", true, true, ProbeOutcome{ObservedAt: later, Reachability: context.DeadlineExceeded}))
if !bad.LastSuccessAt.Equal(now) || bad.ConsecutiveFailures != 1 {
t.Fatalf("after one failure = %+v", bad)
}
bad2 := tracker.apply("postgres", classify("postgres", "PostgreSQL", true, true, ProbeOutcome{ObservedAt: bad.ObservedAt.Add(time.Minute), Reachability: context.DeadlineExceeded}))
if bad2.ConsecutiveFailures != 2 {
t.Fatalf("streak = %d", bad2.ConsecutiveFailures)
}
good := tracker.apply("postgres", classify("postgres", "PostgreSQL", true, true, ProbeOutcome{ObservedAt: bad2.ObservedAt.Add(time.Minute)}))
if good.ConsecutiveFailures != 0 || !good.LastSuccessAt.Equal(bad2.ObservedAt.Add(time.Minute)) {
t.Fatalf("recovered = %+v", good)
}
// Unknown probes (not configured) must not reset or extend a real streak.
neutral := tracker.apply("postgres", classify("postgres", "PostgreSQL", false, true, ProbeOutcome{ObservedAt: good.ObservedAt.Add(time.Minute)}))
if neutral.ConsecutiveFailures != 0 {
t.Fatalf("neutral streak = %d", neutral.ConsecutiveFailures)
}
}
func TestSanitizeProbeErrorTruncatesLongMessages(t *testing.T) {
long := errors.New(fmt.Sprintf("%0200d", 1))
if got := sanitizeProbeError(long); len(got) > 160 {
t.Fatalf("len=%d", len(got))
}
}