Give every engine a key only the router holds
Engines listen on every address their node has, with no key. Checked on the live cluster: from a neighbouring node, a request straight to an engine's port was answered — past the gateway's authentication, quotas and accounting, by anyone who could reach the node. Each replica's engine is now started with a key and refuses requests without it. The key is derived from the replica id with an HMAC over a secret kept in the store, rather than stored per replica: the router has to send the right key to replicas this process never started — adopted after a restart, or placed by the other control plane — and a function of a shared secret gives that without a table to keep in step. A key taken from one node opens that replica only. The secret is made on first use and copied with the rest of the store when moving to PostgreSQL; a new one would lock the router out of every running engine at the moment of the move. The key reaches llama.cpp and vLLM through their environment (LLAMA_API_KEY, VLLM_API_KEY) rather than their command line, which every user on the node can read; SGLang only takes it as an argument. The agent's readiness check, the router's proxy and its metrics scrape send it, the client's own Authorization still never reaches the engine, and `ctl bench` fetches the key of the replica it is pointed at from the admin API. Engines started before this keep running without a key until their replica is next started. With no store there is nowhere to keep the secret, and engines start without one, with a warning. Also formats two files that went in unformatted. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
This commit is contained in:
1 parent
d167686cf1
commit
9853936e0b
34 files changed
+356
-29
No files matched your search
@@ -2525,7 +2525,11 @@ type StartShard struct {
|
||||
Fabric string `protobuf:"bytes,14,opt,name=fabric,proto3" json:"fabric,omitempty"`
|
||||
// profile_fp identifies the version of the profile, so the agent can say
|
||||
// which one a running shard was started from. The agent never interprets it.
|
||||
ProfileFp string `protobuf:"bytes,15,opt,name=profile_fp,json=profileFp,proto3" json:"profile_fp,omitempty"`
|
||||
ProfileFp string `protobuf:"bytes,15,opt,name=profile_fp,json=profileFp,proto3" json:"profile_fp,omitempty"`
|
||||
// api_key is what the engine demands of every request, derived by the
|
||||
// control plane from the replica id. The router sends it; nothing else
|
||||
// that can reach the node's ports has it.
|
||||
ApiKey string `protobuf:"bytes,16,opt,name=api_key,json=apiKey,proto3" json:"api_key,omitempty"`
|
||||
unknownFields protoimpl.UnknownFields
|
||||
sizeCache protoimpl.SizeCache
|
||||
}
|
||||
@@ -2665,6 +2669,13 @@ func (x *StartShard) GetProfileFp() string {
|
||||
return ""
|
||||
}
|
||||
|
||||
func (x *StartShard) GetApiKey() string {
|
||||
if x != nil {
|
||||
return x.ApiKey
|
||||
}
|
||||
return ""
|
||||
}
|
||||
|
||||
type EngineProfile struct {
|
||||
state protoimpl.MessageState `protogen:"open.v1"`
|
||||
Name string `protobuf:"bytes,1,opt,name=name,proto3" json:"name,omitempty"`
|
||||
@@ -3693,7 +3704,7 @@ const file_llmgw_v1_agent_proto_rawDesc = "" +
|
||||
"\n" +
|
||||
"bytes_done\x18\x02 \x01(\x03R\tbytesDone\x12\x1f\n" +
|
||||
"\vbytes_total\x18\x03 \x01(\x03R\n" +
|
||||
"bytesTotal\"\xd9\x03\n" +
|
||||
"bytesTotal\"\xf2\x03\n" +
|
||||
"\n" +
|
||||
"StartShard\x12\x1d\n" +
|
||||
"\n" +
|
||||
@@ -3716,7 +3727,8 @@ const file_llmgw_v1_agent_proto_rawDesc = "" +
|
||||
"\x04pool\x18\r \x01(\tR\x04pool\x12\x16\n" +
|
||||
"\x06fabric\x18\x0e \x01(\tR\x06fabric\x12\x1d\n" +
|
||||
"\n" +
|
||||
"profile_fp\x18\x0f \x01(\tR\tprofileFp\"\xfd\x02\n" +
|
||||
"profile_fp\x18\x0f \x01(\tR\tprofileFp\x12\x17\n" +
|
||||
"\aapi_key\x18\x10 \x01(\tR\x06apiKey\"\xfd\x02\n" +
|
||||
"\rEngineProfile\x12\x12\n" +
|
||||
"\x04name\x18\x01 \x01(\tR\x04name\x12\x16\n" +
|
||||
"\x06engine\x18\x02 \x01(\tR\x06engine\x12\x1b\n" +
|
||||
|
||||
@@ -524,6 +524,10 @@ message StartShard {
|
||||
// profile_fp identifies the version of the profile, so the agent can say
|
||||
// which one a running shard was started from. The agent never interprets it.
|
||||
string profile_fp = 15;
|
||||
// api_key is what the engine demands of every request, derived by the
|
||||
// control plane from the replica id. The router sends it; nothing else
|
||||
// that can reach the node's ports has it.
|
||||
string api_key = 16;
|
||||
}
|
||||
|
||||
message EngineProfile {
|
||||
|
||||
Reference in new issue
Block a user