[proxy,management] Bound model discovery to the caller's own policies
GET /v1/models was bounded by the provider record's enumerated models, which is
the right bound only while a single policy reaches a provider. Where two teams
share one provider under different allowlists, every caller was offered the
union — each model outside their own policy being a request the guardrail
refuses a moment later. A gateway record enumerating nothing was worse: it
offered the upstream's entire catalogue however narrow the policy was.
Each route now carries one rule per authorising policy — its source groups and
the models it permits — instead of a single flattened list. At request time the
router keeps the rules whose groups intersect the caller's, unions their
models, and intersects that with what the provider serves.
nil and [] stay distinct end to end: a policy setting no allowlist reaches the
router as nil and lifts the restriction for the groups it binds, while an
enabled allowlist with no models arrives as [] and permits nothing. Collapsing
them would let a listing that should offer nothing fall open to everything.
The guardrail's own per-provider allowlist is untouched. It is a fail-closed
backstop that cannot tell who is asking, so discovery is now narrower than the
backstop rather than wider.
[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.
Store the per-account gateway endpoint as {domain, proxy_address} with a
global unique index on the full hostname; dedicated = (domain ==
proxy_address). Bootstrap becomes an explicit POST carrying exactly one
of proxy_address (server allocates an adjective-noun label beneath it)
or endpoint (claimed verbatim, address-first); provider create loses its
bootstrap side effect. PUT is a full replace with every field required —
the immutable identity fields must be echoed unchanged and a mismatch is
rejected with 422. A guarded DELETE releases the endpoint: refused with
412 while providers exist or a proxy is actively serving the endpoint
hostname (matched case-insensitively); re-creating bootstraps fresh. A
self-addressed pin excludes its address from the account's cluster allow
list, and the live mapping update path now addresses the serving proxy
from the synthesized service. Existing rows are migrated on all three
store engines.
