OpenShell/proto/inference.proto

// SPDX-FileCopyrightText: Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
// SPDX-License-Identifier: Apache-2.0

syntax = "proto3";

package openshell.inference.v1;

option java_multiple_files = true;
option java_package = "com.anthropic.openshell.inference.v1";

// Inference service provides cluster inference configuration and bundle delivery.
service Inference {
  // Return the resolved inference route bundle for sandbox-local execution.
  rpc GetInferenceBundle(GetInferenceBundleRequest)
      returns (GetInferenceBundleResponse);

  // Set cluster-level inference configuration.
  //
  // This controls how requests sent to `inference.local` are routed.
  rpc SetClusterInference(SetClusterInferenceRequest)
      returns (SetClusterInferenceResponse);

  // Get cluster-level inference configuration.
  rpc GetClusterInference(GetClusterInferenceRequest)
      returns (GetClusterInferenceResponse);

}

// Persisted cluster inference configuration.
//
// Only `provider_name` and `model_id` are stored; endpoint, protocols,
// credentials, and auth style are resolved from the provider at bundle time.
message ClusterInferenceConfig {
  // Provider record name backing this route.
  string provider_name = 1;
  // Model identifier to force on generation calls.
  string model_id = 2;
}

// Storage envelope for the managed cluster inference route.
message InferenceRoute {
  string id = 1;
  ClusterInferenceConfig config = 2;
  // Object name ("inference.local" for the user-facing route,
  // "sandbox-system" for the sandbox system-level route).
  string name = 3;
  // Monotonic version incremented on every update.
  uint64 version = 4;
}

message SetClusterInferenceRequest {
  // Provider record name to use for credentials + endpoint mapping.
  string provider_name = 1;
  // Model identifier to force on generation calls.
  string model_id = 2;
  // Route name to target. Empty string defaults to "inference.local" (user-facing).
  // Use "sandbox-system" for the sandbox system-level inference route.
  string route_name = 3;
  // Verify the resolved upstream endpoint synchronously before persistence.
  bool verify = 4;
  // Skip synchronous endpoint validation before persistence.
  bool no_verify = 5;
}

message ValidatedEndpoint {
  string url = 1;
  string protocol = 2;
}

message SetClusterInferenceResponse {
  string provider_name = 1;
  string model_id = 2;
  uint64 version = 3;
  // Route name that was configured.
  string route_name = 4;
  // Whether endpoint verification ran as part of this request.
  bool validation_performed = 5;
  // The concrete endpoints that were probed during validation, when available.
  repeated ValidatedEndpoint validated_endpoints = 6;
}

message GetClusterInferenceRequest {
  // Route name to query. Empty string defaults to "inference.local" (user-facing).
  // Use "sandbox-system" for the sandbox system-level inference route.
  string route_name = 1;
}

message GetClusterInferenceResponse {
  string provider_name = 1;
  string model_id = 2;
  uint64 version = 3;
  // Route name that was queried.
  string route_name = 4;
}

message GetInferenceBundleRequest {}

// A single resolved route ready for sandbox-local execution.
message ResolvedRoute {
  string name = 1;
  string base_url = 2;
  repeated string protocols = 3;
  string api_key = 4;
  string model_id = 5;
  string provider_type = 6;
}

message GetInferenceBundleResponse {
  repeated ResolvedRoute routes = 1;
  // Opaque revision tag for cache freshness checks.
  string revision = 2;
  // Timestamp (epoch ms) when this bundle was generated.
  int64 generated_at_ms = 3;
}