[proxy,management] Conform the Agent Network endpoint to the LLM gateway protocol (#7154)

[proxy,management] Conform the Agent Network endpoint to the LLM gateway protocol

Reviewed the proxy against Claude Code's published gateway contract. The
transport layer already held up; fourteen gaps sat one layer up, in the model
catalog and in the non-inference endpoints clients call.

Two of them cost money. The catalog carried no claude-opus-5 or
claude-sonnet-5, so an operator could not authorise the models coding agents
default to — those requests denied as not-routable, or priced at zero where a
catch-all carried them. And gateway records pin ParserID "openai" while the
same record serves /v1/messages, so Anthropic responses were read with the
OpenAI parser, which never looks at message_start where input tokens live:
input metered as roughly zero on every stream and cost was skipped entirely.

The rest fix requests refused for structural rather than policy reasons: model
discovery denied for every account with a model allowlist, token counting
denied on Bedrock and mis-parsed on Vertex, startup probes refused and written
into the access log at every session start, and denials rendered in a shape no
LLM client parses. Two changes are additive by design — the deny body keeps
every field it had and adds the vendor's error object alongside, and body-level
identity injection is now gated on the request's dialect so it stops sending
OpenAI-shape fields into Anthropic bodies that reject them.

The end-to-end work turned up one more: the discovery filter treated any slash
in a model id as a gateway prefix, which would have dropped every self-hosted
"Qwen/..." model from the picker.
This commit is contained in:
Maycon Santos
2026-08-23 20:02:33 +02:00
committed by GitHub
parent ee253feddf
commit 766fcae3f8
39 changed files with 3094 additions and 154 deletions
@@ -61,6 +61,8 @@ func (middlewareImpl) MetadataKeys() []string {
middleware.KeyLLMRequestPromptRaw,
middleware.KeyLLMCaptureTruncated,
middleware.KeyLLMSessionID,
middleware.KeyLLMAgentID,
middleware.KeyLLMParentAgentID,
}
}
@@ -72,9 +74,9 @@ func (middlewareImpl) Close() error { return nil }
// Invoke detects the LLM provider, parses request facts, and emits
// metadata. Always returns DecisionAllow; never errors. Provider
// selection prefers the configured providerID (synthesiser-stamped on
// agent-network targets) so requests routed to a custom upstream URL
// still resolve. Falls back to URL sniffing when no providerID is set.
// selection prefers the request path, falling back to the configured
// providerID (synthesiser-stamped on agent-network targets) so requests
// routed to a custom upstream URL still resolve.
func (m middlewareImpl) Invoke(_ context.Context, in *middleware.Input) (*middleware.Output, error) {
out := &middleware.Output{Decision: middleware.DecisionAllow}
if in == nil {
@@ -92,9 +94,14 @@ func (m middlewareImpl) Invoke(_ context.Context, in *middleware.Input) (*middle
return m.invokeBedrock(in, br), nil
}
parser, ok := llm.ParserByName(m.providerID)
// A path that names an API surface wins over the configured providerID:
// a gateway record pinned to "openai" still serves Claude Code on
// /v1/messages, and reading that body with the OpenAI parser loses the
// Anthropic usage block and prices the request on the wrong surface.
// providerID stays the fallback for upstreams whose path says nothing.
parser, ok := llm.DetectParser(extractPath(in.URL))
if !ok {
parser, ok = llm.DetectParser(extractPath(in.URL))
parser, ok = llm.ParserByName(m.providerID)
}
if !ok {
return out, nil
@@ -116,9 +123,9 @@ func (m middlewareImpl) Invoke(_ context.Context, in *middleware.Input) (*middle
}
appendSessionID := func(md []middleware.KV) []middleware.KV {
if sessionID != "" {
return append(md, middleware.KV{Key: middleware.KeyLLMSessionID, Value: sessionID})
md = append(md, middleware.KV{Key: middleware.KeyLLMSessionID, Value: sessionID})
}
return md
return appendAgentIDs(md, in.Headers)
}
facts, err := parser.ParseRequest(in.Body)
@@ -160,6 +167,41 @@ func (m middlewareImpl) Invoke(_ context.Context, in *middleware.Input) (*middle
return out, nil
}
// agentIDHeader and parentAgentIDHeader carry sub-agent attribution: a
// coding agent that spawns helpers stamps the spawned agent's id, plus the
// spawning agent's when that helper is itself nested. Both are opaque
// identifiers rather than content, so they're emitted regardless of the
// prompt-collection toggle, the same way the session id is.
const (
agentIDHeader = "x-claude-code-agent-id"
parentAgentIDHeader = "x-claude-code-parent-agent-id"
)
// appendAgentIDs stamps the sub-agent attribution headers onto the metadata
// bag, skipping either one the request doesn't carry.
func appendAgentIDs(md []middleware.KV, headers []middleware.KV) []middleware.KV {
for _, pair := range []struct{ key, header string }{
{middleware.KeyLLMAgentID, agentIDHeader},
{middleware.KeyLLMParentAgentID, parentAgentIDHeader},
} {
if v := headerValue(headers, pair.header); v != "" {
md = append(md, middleware.KV{Key: pair.key, Value: v})
}
}
return md
}
// headerValue returns the first non-empty value for the named header.
// Headers arrive in canonical form, so the match is case-insensitive.
func headerValue(headers []middleware.KV, want string) string {
for _, kv := range headers {
if strings.EqualFold(kv.Key, want) && kv.Value != "" {
return kv.Value
}
}
return ""
}
// sessionIDHeaders are request header names that may carry a client
// session identifier, checked in order, case-insensitively. Matching is
// against Go's canonical header form, so use the hyphenated names the
@@ -173,10 +215,8 @@ var sessionIDHeaders = []string{"x-claude-code-session-id", "session-id", "x-ses
// canonical form, so the match is case-insensitive.
func sessionIDFromHeaders(headers []middleware.KV) string {
for _, want := range sessionIDHeaders {
for _, kv := range headers {
if strings.EqualFold(kv.Key, want) && kv.Value != "" {
return kv.Value
}
if v := headerValue(headers, want); v != "" {
return v
}
}
return ""
@@ -252,6 +292,12 @@ func parseVertexPath(reqPath string) (vertexRequest, bool) {
if c := strings.LastIndex(rest, ":"); c >= 0 {
model, action = rest[:c], rest[c+1:]
}
// Token counting hangs off the model as its own path segment
// (".../models/{model}/count-tokens:rawPredict"), so anything past the
// first "/" belongs to the method rather than the model id.
if slash := strings.Index(model, "/"); slash >= 0 {
model = model[:slash]
}
model = llm.NormalizeVertexModel(model)
if model == "" {
return vertexRequest{}, false
@@ -298,6 +344,7 @@ func (m middlewareImpl) invokeVertex(in *middleware.Input, vx vertexRequest) *mi
if sessionID != "" {
md = append(md, middleware.KV{Key: middleware.KeyLLMSessionID, Value: sessionID})
}
md = appendAgentIDs(md, in.Headers)
promptTruncated := false
if parser != nil && m.capturePrompt {
@@ -345,7 +392,9 @@ func trimBedrockNamespace(reqPath string) string {
//
// /model/{modelId}/{action}
//
// action ∈ {invoke, invoke-with-response-stream, converse, converse-stream}.
// action ∈ {invoke, invoke-with-response-stream, converse, converse-stream,
// count-tokens}. Token counting carries a model and no usage, so it routes
// like any other action and meters to zero.
// The modelId may be URL-encoded and may carry a cross-region inference-profile
// prefix and a version suffix; normalizeBedrockModel strips both so the model
// matches catalog pricing.
@@ -369,7 +418,7 @@ func parseBedrockPath(reqPath string) (bedrockRequest, bool) {
return bedrockRequest{}, false
}
switch action {
case "invoke", "converse":
case "invoke", "converse", "count-tokens":
return bedrockRequest{model: model}, true
case "invoke-with-response-stream", "converse-stream":
return bedrockRequest{model: model, stream: true}, true
@@ -397,6 +446,7 @@ func (m middlewareImpl) invokeBedrock(in *middleware.Input, br bedrockRequest) *
if sessionID != "" {
md = append(md, middleware.KV{Key: middleware.KeyLLMSessionID, Value: sessionID})
}
md = appendAgentIDs(md, in.Headers)
promptTruncated := false
if parser != nil && m.capturePrompt {