fix(startup): 密钥警告改读真实生效的 key 集合

启动时那条「gateway_keys is EMPTY — without a key every request is rejected」
读的是 legacy 的 cfg.GatewayKeys 段,而鉴权实际用 cfg.Keys(core.ListKeys)。
seedKeys 首次启动把 gateway_keys 搬进 keys[] 之后,YAML 里那个列表就不再
被鉴权使用。于是在它被清空(例如轮换掉 starter key 之后)而 keys[] 仍有
7 把可用 key(含 admin)时,进程每次启动都谎报「所有请求都会被拒绝」。

实测:生产日志出现该警告,而同一个 key 请求 /v1/models 返回 200。

- main.go 改为检查 c.ListKeys(),文案改成不绑定字段名。
- 顺带删掉 gateway.New 的 gatewayKeys 参数:函数体从未使用它,
  只读 ListKeys(),留着会继续诱导人以为鉴权来自那个列表。

判据:e2e/TestStartupWarningReflectsRealKeysNotLegacyList —— 构造
「gateway_keys 空 + keys[] 有 key」的真实形态,先断言该 key 确实能鉴权,
再断言日志里不再出现那句谎报。变异验证:回退成 GatewayKeys() 即变红。
This commit is contained in:
JianFeeeee
2026-09-28 23:42:48 +08:00
parent 04e544c823
commit 70f1c879bd
6 changed files with 159 additions and 11 deletions

View File

@ -326,3 +326,144 @@ func statusOf(resp *http.Response) int {
}
return resp.StatusCode
}
// The startup warning about key configuration must describe the key set that
// AUTH actually uses (cfg.Keys, via core.ListKeys), not the legacy
// gateway_keys YAML list.
//
// It used to check GatewayKeys() only. seedKeys copies gateway_keys into keys[]
// on first start and the YAML list stops being consulted, so once that list was
// emptied — e.g. after rotating the starter key away — the process logged
// "every request will be rejected" while seven working keys, one of them admin,
// were in service. Observed in production: the warning appeared and that same
// key returned HTTP 200 on /v1/models.
//
// The fixture reproduces exactly that shape: gateway_keys EMPTY, with the
// working key present only in keys[].
func TestStartupWarningReflectsRealKeysNotLegacyList(t *testing.T) {
up := newMockUpstream(t)
dir := t.TempDir()
// Seed a real install once so keys[] gets populated from gateway_keys, then
// rewrite the file to look like a rotated install: legacy list cleared, the
// seeded key still present in keys[].
path := writeConfig(t, dir, "127.0.0.1:0", map[string]*mockUpstream{"good": up})
bin := buildBinary(t)
// First run creates the sealed config with keys[] populated.
seedPort := freePort(t)
cfg1 := writeConfig(t, dir, "127.0.0.1:"+seedPort, map[string]*mockUpstream{"good": up})
g1 := startGateway(t, bin, "127.0.0.1:"+seedPort, cfg1)
g1.stop()
data, err := os.ReadFile(cfg1)
if err != nil {
t.Fatal(err)
}
if !strings.Contains(string(data), "keys:") {
t.Fatalf("first run did not populate keys[]:\n%s", data)
}
// Now clear the legacy gateway_keys list, keeping keys[] intact. The
// rewritten file may use different indentation, so match loosely.
cleared, n := clearGatewayKeys(string(data))
if n == 0 {
t.Fatalf("could not find a gateway_keys entry to clear in:\n%s", data)
}
if err := os.WriteFile(cfg1, []byte(cleared), 0o644); err != nil {
t.Fatal(err)
}
// Start again and inspect the log. The config pins its listen address, so
// rewrite that field to the port we will actually poll.
port2 := freePort(t)
rehosted, ok := replaceListen(string(cleared), "127.0.0.1:"+port2)
if !ok {
t.Fatalf("could not rewrite listen in:\n%s", cleared)
}
cfg2 := filepath.Join(dir, "config2.yaml")
if err := os.WriteFile(cfg2, []byte(rehosted), 0o644); err != nil {
t.Fatal(err)
}
g2 := startGateway(t, bin, "127.0.0.1:"+port2, cfg2)
defer g2.stop()
// Sanity: the key really does authenticate, so the warning would be a lie.
resp, _ := g2.do("GET", "/v1/models", "", true)
if resp == nil || resp.StatusCode != http.StatusOK {
t.Fatalf("key from keys[] did not authenticate (status %v); test fixture is wrong",
resp)
}
logs := g2.logString()
if strings.Contains(logs, "gateway_keys is EMPTY") {
t.Errorf("startup logged 'gateway_keys is EMPTY ... every request is rejected' while "+
"a working admin key was in service — the warning must read the authoritative "+
"key set (core.ListKeys), not the legacy YAML list.\nlog:\n%s", logs)
}
_ = path
_ = g1
}
func freePort(t *testing.T) string {
t.Helper()
l, err := net.Listen("tcp", "127.0.0.1:0")
if err != nil {
t.Fatal(err)
}
defer l.Close()
_, port, _ := net.SplitHostPort(l.Addr().String())
return port
}
// stop terminates the gateway and waits, so its log buffer is complete.
func (g *gatewayUnderTest) stop() {
if g == nil || g.cmd == nil || g.cmd.Process == nil {
return
}
_ = g.cmd.Process.Kill()
_, _ = g.cmd.Process.Wait()
}
// logString returns everything the gateway has written so far.
func (g *gatewayUnderTest) logString() string { return g.log.String() }
// clearGatewayKeys empties the gateway_keys list in a config, tolerating any
// indentation the YAML writer chose. Returns the new text and how many entries
// it removed.
func clearGatewayKeys(src string) (string, int) {
lines := strings.Split(src, "\n")
var out []string
removed := 0
inList := false
for _, l := range lines {
trimmed := strings.TrimSpace(l)
if strings.HasPrefix(l, "gateway_keys:") {
out = append(out, "gateway_keys: []")
inList = true
removed++
continue
}
if inList {
if strings.HasPrefix(trimmed, "- ") {
removed++
continue
}
inList = false
}
out = append(out, l)
}
return strings.Join(out, "\n"), removed
}
// replaceListen rewrites the top-level listen: value.
func replaceListen(src, addr string) (string, bool) {
lines := strings.Split(src, "\n")
for i, l := range lines {
if strings.HasPrefix(l, "listen:") {
lines[i] = "listen: " + addr
return strings.Join(lines, "\n"), true
}
}
return src, false
}