mirror of
https://github.com/Buriburizaem0n/nezha_domains.git
synced 2026-09-19 09:40:12 +00:00
naibaandcloudcode
e8dabf5bc6
Introduce Personal Access Tokens (nzp_*) as a stateless auth path alongside
JWT, gated per-endpoint by a scope middleware (nezha:{resource}:{verb}) with
fail-closed empty-scope defaults and a server-id whitelist. Self-management
endpoints (profile, api-tokens, oauth2 bind, refresh-token) explicitly reject
PATs to block privilege-escalation chains. A revoke registry tears down active
long-lived connections (terminal, fm, ws, transfer, mcp) the moment a PAT is
deleted, with a tombstone closing the revoke->register race.
Add an MCP endpoint that proxies tool calls (exec, fs read/write/delete,
transfer) to agents over gRPC, guarded by origin/DNS-rebinding checks, a
per-token rate limiter, audit logging, and a kill switch. Serialize all
sends through the IOStream wrapper to honour grpc-go's concurrency contract.
Add CSRF double-submit protection on unsafe cookie-authenticated methods,
exempting authenticated PAT requests by context identity (not a forgeable
Authorization header). Apply visibility/whitelist filtering consistently
across list, get-by-id, and mutate paths to enforce tenant isolation.
Migrate legacy mcp:* scopes: rewrite read/exec to nezha:* equivalents and
drop dangerous write/delete/wildcard grants.
Co-authored-by: cloudcode <cloudcode@users.noreply.github.com>
81 lines
2.6 KiB
Go
81 lines
2.6 KiB
Go
package rpc
|
|
|
|
import (
|
|
"context"
|
|
"errors"
|
|
"sync"
|
|
"testing"
|
|
"time"
|
|
|
|
"github.com/nezhahq/nezha/model"
|
|
)
|
|
|
|
// Registration-after-sweep race (review issue #1): CancelAllMCPInflight only
|
|
// cancels entries already present in the inflight map. A CallAgent that passes
|
|
// the upfront kill-switch check but has not yet Store()d its entry is invisible
|
|
// to the sweep, so without a post-registration re-check it goes on to SendTask
|
|
// a fresh exec/fs task to the agent AFTER EnableMCP=false.
|
|
//
|
|
// This test drives the worst-case interleaving deterministically:
|
|
// 1. CallAgent passes the upfront observer check (observer still false).
|
|
// 2. The operator flips the observer to "disabled" and runs the cancel sweep
|
|
// while CallAgent is paused between the check and Store.
|
|
// 3. CallAgent resumes; it MUST observe the kill switch on the post-Store
|
|
// re-check and return ErrMCPDisabled WITHOUT sending the task.
|
|
//
|
|
// With the race present, CallAgent sends the task and blocks until timeout
|
|
// (ErrAgentTimeout) — the agent received a fresh task past the kill switch.
|
|
func TestCallAgent_KillSwitchBeatsRegistrationAfterSweep(t *testing.T) {
|
|
const target uint64 = 7401
|
|
|
|
stream := newFakeStream()
|
|
cleanup := installFakeServer(t, target, stream)
|
|
defer cleanup()
|
|
|
|
var killed bool
|
|
var mu sync.Mutex
|
|
prev := mcpKillSwitchObserver()
|
|
// Observer returns the operator-controlled flag. CallAgent reads it both
|
|
// before and (with the fix) after registering the inflight entry.
|
|
SetMCPKillSwitchObserver(func() bool {
|
|
mu.Lock()
|
|
defer mu.Unlock()
|
|
return killed
|
|
})
|
|
t.Cleanup(func() { SetMCPKillSwitchObserver(prev) })
|
|
|
|
// Fail loudly if the agent ever receives a task: that means a fresh call
|
|
// leaked past the kill switch.
|
|
leaked := make(chan *struct{}, 1)
|
|
go func() {
|
|
select {
|
|
case <-stream.sent:
|
|
leaked <- nil
|
|
case <-time.After(2 * time.Second):
|
|
}
|
|
}()
|
|
|
|
// Arrange the interleaving: hook fires once CallAgent is about to register,
|
|
// flipping the kill switch and running the cancel sweep so the not-yet-Stored
|
|
// entry is missed by the sweep.
|
|
testKillSwitchAfterUpfrontCheck = func() {
|
|
mu.Lock()
|
|
killed = true
|
|
mu.Unlock()
|
|
CancelAllMCPInflight()
|
|
}
|
|
t.Cleanup(func() { testKillSwitchAfterUpfrontCheck = nil })
|
|
|
|
_, err := CallAgent(context.Background(), target, model.TaskTypeExec,
|
|
model.ExecRequest{Cmd: "x"}, 1*time.Second)
|
|
|
|
if !errors.Is(err, ErrMCPDisabled) {
|
|
t.Fatalf("CallAgent must return ErrMCPDisabled when the kill switch fires during registration; got %v", err)
|
|
}
|
|
select {
|
|
case <-leaked:
|
|
t.Fatal("a fresh MCP task leaked to the agent past the kill switch")
|
|
default:
|
|
}
|
|
}
|