> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/nemo/relay/_mcp/server.

# Module nvidia_worker_v1

> Typed worker contract introduced alongside the legacy API.

Generated from `cargo doc --no-deps -p nemo-relay-builtins -p nemo-relay-diagnostics -p nemo-relay-logging -p nemo-relay-plugin-host -p nemo-relay-codecs -p nemo-relay -p nemo-relay-runtime -p nemo-relay-model-pricing -p nemo-relay-resource-metrics -p nemo-relay-observability -p nemo-relay-adaptive -p nemo-relay-pii-redaction -p nemo-relay-ffi -p nemo-relay-types -p nemo-relay-plugin -p nemo-relay-worker-proto -p nemo-relay-worker`.

Typed worker contract introduced alongside the legacy API.

## Modules

* [content_part](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/content_part): Nested message and enum types in `ContentPart`.
* [decode_llm_codec_request_response](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/decode_llm_codec_request_response): Nested message and enum types in `DecodeLlmCodecRequestResponse`.
* [decode_llm_codec_response_response](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/decode_llm_codec_response_response): Nested message and enum types in `DecodeLlmCodecResponseResponse`.
* [diagnostic_code_definition](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/diagnostic_code_definition): Nested message and enum types in `DiagnosticCodeDefinition`.
* [encode_llm_codec_request_response](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/encode_llm_codec_request_response): Nested message and enum types in `EncodeLlmCodecRequestResponse`.
* [event](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/event): Nested message and enum types in `Event`.
* [finish_reason](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/finish_reason): Nested message and enum types in `FinishReason`.
* [get_current_scope_stack_snapshot_response](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/get_current_scope_stack_snapshot_response): Nested message and enum types in `GetCurrentScopeStackSnapshotResponse`.
* [get_diagnostic_discovery_response](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/get_diagnostic_discovery_response): Nested message and enum types in `GetDiagnosticDiscoveryResponse`.
* [guardrail_decision](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/guardrail_decision): Nested message and enum types in `GuardrailDecision`.
* [inspect_diagnostic_memory_response](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/inspect_diagnostic_memory_response): Nested message and enum types in `InspectDiagnosticMemoryResponse`.
* [invoke_request](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/invoke_request): Nested message and enum types in `InvokeRequest`.
* [invoke_response](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/invoke_response): Nested message and enum types in `InvokeResponse`.
* [invoke_stream_response](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/invoke_stream_response): Nested message and enum types in `InvokeStreamResponse`.
* [llm_message](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/llm_message): Nested message and enum types in `LlmMessage`.
* [llm_next_response](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/llm_next_response): Nested message and enum types in `LlmNextResponse`.
* [llm_stream_next_response](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/llm_stream_next_response): Nested message and enum types in `LlmStreamNextResponse`.
* [memory_limit_event_slot](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/memory_limit_event_slot): Nested message and enum types in `MemoryLimitEventSlot`.
* [message_content](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/message_content): Nested message and enum types in `MessageContent`.
* [plugin_worker_service_client](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/plugin_worker_service_client): Generated client implementations.
* [plugin_worker_service_server](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/plugin_worker_service_server): Generated server implementations.
* [read_diagnostic_page_response](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/read_diagnostic_page_response): Nested message and enum types in `ReadDiagnosticPageResponse`.
* [register_response](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/register_response): Nested message and enum types in `RegisterResponse`.
* [relay_diagnostics_service_client](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/relay_diagnostics_service_client): Generated client implementations.
* [relay_diagnostics_service_server](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/relay_diagnostics_service_server): Generated server implementations.
* [relay_host_runtime_service_client](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/relay_host_runtime_service_client): Generated client implementations.
* [relay_host_runtime_service_server](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/relay_host_runtime_service_server): Generated server implementations.
* [resource_memory_number](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/resource_memory_number): Nested message and enum types in `ResourceMemoryNumber`.
* [resource_memory_unit](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/resource_memory_unit): Nested message and enum types in `ResourceMemoryUnit`.
* [runtime_registration_owner](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/runtime_registration_owner): Nested message and enum types in `RuntimeRegistrationOwner`.
* [submit_diagnostic_request](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/submit_diagnostic_request): Nested message and enum types in `SubmitDiagnosticRequest`.
* [tool_choice](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/tool_choice): Nested message and enum types in `ToolChoice`.
* [tool_definition](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/tool_definition): Nested message and enum types in `ToolDefinition`.
* [tool_next_response](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/tool_next_response): Nested message and enum types in `ToolNextResponse`.
* [validate_response](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/validate_response): Nested message and enum types in `ValidateResponse`.

## Structs

* [AnnotatedLlmRequest](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-annotatedllmrequest): Normalized request structure with explicit provider-specific and extension fields.
* [AnnotatedLlmResponse](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-annotatedllmresponse): Normalized completed response, usage, pricing, and optimization evidence.
* [AssistantMessage](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-assistantmessage): Assistant output with independently optional content and tool calls.
* [BaseEvent](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-baseevent): Common ATOF identity, propagation, timing, and application payload fields.
* [CacheWriteTokenCounts](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-cachewritetokencounts): Prompt-cache write tokens retained for one cache duration.
* [CacheWriteTokenCountsList](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-cachewritetokencountslist): Presence-bearing duration-aware prompt-cache write counts.
* [CancelInvocationRequest](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-cancelinvocationrequest): Requests cancellation of one active invocation without replaying work.
* [CancelInvocationResponse](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-cancelinvocationresponse): Idempotent: unknown/completed IDs return accepted=false, without resurrecting work.
* [CategoryProfile](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-categoryprofile): Known category-specific fields and lossless extensions attached to an event.
* [ComponentMemoryFootprint](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-componentmemoryfootprint): Typed component memory footprint preserving the shared runtime fields.
* [ComponentMemoryUsage](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-componentmemoryusage): Typed component memory usage preserving the shared runtime fields.
* [ConditionalMiddlewareGuardrailRegistration](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-conditionalmiddlewareguardrailregistration): Declares a static or callback-based filter over runtime registrations.
* [ConditionalMiddlewareInvocation](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-conditionalmiddlewareinvocation): Asks a conditional callback whether selected middleware registrations may execute.
* [ConfigDiagnostic](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-configdiagnostic): Structured configuration warning or error with optional component and field location.
* [ConfigDiagnostics](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-configdiagnostics): Present validation result; an empty list is successful validation without diagnostics.
* [ContentPart](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-contentpart): Selects a normalized content block or a lossless provider-native block.
* [ContentPartList](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-contentpartlist): Ordered multimodal content; a present empty list remains an explicit variant.
* [CostEstimate](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-costestimate): Normalized monetary cost with provenance for estimates and provider-reported values.
* [CreateScopeStackRequest](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-createscopestackrequest): Creates an isolated host-owned scope stack for this activation.
* [CreateScopeStackResponse](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-createscopestackresponse): Returns the new isolated stack's opaque binding identity.
* [Credentials](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-credentials): Required on authenticated requests. Both strings must match the activation.
* [DataSchema](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-dataschema): Application-owned schema identity; its version is not the worker version.
* [DecodeLlmCodecRequestRequest](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-decodellmcodecrequestrequest): Requests normalized decoding through an invocation-bound request codec.
* [DecodeLlmCodecRequestResponse](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-decodellmcodecrequestresponse): Selects the normalized request or the codec's domain failure.
* [DecodeLlmCodecResponseRequest](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-decodellmcodecresponserequest): Requests normalized decoding through an invocation-bound response codec.
* [DecodeLlmCodecResponseResponse](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-decodellmcodecresponseresponse): Selects the normalized completed response or the codec's domain failure.
* [DeregisterConditionalMiddlewareGuardrailRequest](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-deregisterconditionalmiddlewareguardrailrequest): Removes a conditional guardrail using its activation-owned handle.
* [DeregisterConditionalMiddlewareGuardrailResponse](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-deregisterconditionalmiddlewareguardrailresponse): Reports whether an owned conditional guardrail was removed.
* [DiagnosticCapabilities](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-diagnosticcapabilities): Host-owned limits and contract identities required for diagnostic admission.
* [DiagnosticCapability](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-diagnosticcapability): Availability and optional reason for one named diagnostic feature.
* [DiagnosticClassification](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-diagnosticclassification): Preserves catalogue and failure-class names, including unknown future names.
* [DiagnosticCodeDefinition](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-diagnosticcodedefinition): Selects an existing catalogue name or an activation-local extension definition.
* [DiagnosticComponentClose](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-diagnosticcomponentclose): Closes a component handle without deleting its retained accounting.
* [DiagnosticComponentIdentity](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-diagnosticcomponentidentity): Identifies a logical component and one registration incarnation.
* [DiagnosticComponentOwnership](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-diagnosticcomponentownership): Correlates component responsibility without creating additional counter dimensions.
* [DiagnosticComponentRegistration](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-diagnosticcomponentregistration): Registers a bounded diagnostic component and an ordered list of code handles.
* [DiagnosticComponentSnapshot](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-diagnosticcomponentsnapshot): A retained component row with lifetime, refresh, counters, and windows.
* [DiagnosticCorrelation](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-diagnosticcorrelation): Optional trajectory correlation, excluded from aggregation keys.
* [DiagnosticCount](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-diagnosticcount): Unsigned count that stops at its maximum. After that limit, it is a lower bound.
* [DiagnosticCounter](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-diagnosticcounter): Lifetime occurrence count and latest observation time for one admitted code.
* [DiagnosticCoverage](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-diagnosticcoverage): Describes snapshot availability, aggregation scope, retention, and evidence loss.
* [DiagnosticCursor](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-diagnosticcursor): Canonical snapshot position; it does not grant transport read authority.
* [DiagnosticDetail](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-diagnosticdetail): Retained diagnostic text with explicit truncation state.
* [DiagnosticDiscovery](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-diagnosticdiscovery): Typed diagnostic discovery preserving the shared runtime fields.
* [DiagnosticEvent](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-diagnosticevent): One retained observation, its attribution, occurrence delta, and optional evidence.
* [DiagnosticExtensionDefinition](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-diagnosticextensiondefinition): Declares one plugin-defined diagnostic classification and its allowed causes.
* [DiagnosticLifetimeSummary](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-diagnosticlifetimesummary): Lifetime totals and monotonic elapsed time for a source or component.
* [DiagnosticLoss](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-diagnosticloss): Explicit counters for bounded-storage, admission, and projection losses.
* [DiagnosticMemoryPage](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-diagnosticmemorypage): Typed diagnostic memory page preserving the shared runtime fields.
* [DiagnosticMemoryUsage](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-diagnosticmemoryusage): Typed diagnostic memory usage preserving the shared runtime fields.
* [DiagnosticObservation](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-diagnosticobservation): Records a positive occurrence delta using admitted component and code handles.
* [DiagnosticOrigin](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-diagnosticorigin): Captures the refresh generation and ownership at observation time.
* [DiagnosticPluginContext](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-diagnosticplugincontext): Carries independently optional plugin execution and lifecycle phase names.
* [DiagnosticProducerSupport](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-diagnosticproducersupport): Typed diagnostic producer support preserving the shared runtime fields.
* [DiagnosticQuery](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-diagnosticquery): Typed diagnostic query preserving the shared runtime fields.
* [DiagnosticReceipt](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-diagnosticreceipt): Reports sequence consumption, admission outcome, and retained evidence disposition.
* [DiagnosticRefreshSummary](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-diagnosticrefreshsummary): Accounting for the component's current refresh generation and ownership.
* [DiagnosticRetention](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-diagnosticretention): Reports retained bounds and whether the requested page was truncated.
* [DiagnosticSnapshot](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-diagnosticsnapshot): JSON output represents every uint64 diagnostic counter as a decimal string.
* [DiagnosticSourceIdentity](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-diagnosticsourceidentity): Identifies the process incarnation that owns diagnostic accounting.
* [DiagnosticTotals](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-diagnostictotals): Outcome and recording totals for an explicitly identified accounting scope.
* [DiagnosticWindow](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-diagnosticwindow): Bounded outcome history at one configured time resolution.
* [DiagnosticWindowBucket](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-diagnosticwindowbucket): Outcome counts for one source-local elapsed-time interval.
* [DiagnosticWindowCoverage](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-diagnosticwindowcoverage): Reports the temporal extent and completeness of a diagnostic window.
* [DropScopeStackRequest](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-dropscopestackrequest): Releases an activation-owned isolated scope stack.
* [DropScopeStackResponse](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-dropscopestackresponse): Confirms stack release; failures use gRPC status.
* [EmitMarkRequest](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-emitmarkrequest): Requests host materialization of a mark in the selected scope context.
* [EmitMarkResponse](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-emitmarkresponse): Confirms the mark operation completed; failures use gRPC status.
* [EncodeLlmCodecRequestRequest](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-encodellmcodecrequestrequest): Requests provider encoding from an annotation and original request baseline.
* [EncodeLlmCodecRequestResponse](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-encodellmcodecrequestresponse): Selects the encoded provider request or the codec's domain failure.
* [EntryMemoryFootprint](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-entrymemoryfootprint): Typed entry memory footprint preserving the shared runtime fields.
* [EntryMemoryUsage](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-entrymemoryusage): Typed entry memory usage preserving the shared runtime fields.
* [Event](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-event): Exactly one kind is required. UUID strings use canonical hyphenated UUIDs.
* [EventSanitizeFields](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-eventsanitizefields): Sanitizer output replaces these fields; absence clears the corresponding field.
* [FinishReason](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-finishreason): Normalized completion reason with an explicit lossless unknown-name alternative.
* [FunctionCall](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-functioncall): Function name and original argument text, which need not be complete JSON.
* [FunctionDefinition](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-functiondefinition): Function name, optional description and JSON Schema, strictness, and extensions.
* [FunctionMessage](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-functionmessage): Legacy function result; absent content represents explicit null in the runtime DTO.
* [FunctionToolDefinition](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-functiontooldefinition): Function tool definition plus provider fields outside the normalized function.
* [GenerationParams](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-generationparams): Portable generation controls with presence preserved for every optional value.
* [GetCurrentScopeStackSnapshotRequest](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-getcurrentscopestacksnapshotrequest): Queries the scope stack bound to an invocation or selected scope context.
* [GetCurrentScopeStackSnapshotResponse](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-getcurrentscopestacksnapshotresponse): Selects a present snapshot or an explicit absence of bound context.
* [GetDiagnosticCapabilitiesRequest](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-getdiagnosticcapabilitiesrequest): Queries diagnostic policy using activation credentials, without opening a session.
* [GetDiagnosticCapabilitiesResponse](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-getdiagnosticcapabilitiesresponse): Returns the host's bounded diagnostic delivery and read policy.
* [GetDiagnosticDiscoveryRequest](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-getdiagnosticdiscoveryrequest): Requests discovery evidence only under the activation's separately granted read authority.
* [GetDiagnosticDiscoveryResponse](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-getdiagnosticdiscoveryresponse): Returns discovery evidence or a portable domain read failure; transport failures use gRPC status.
* [GetRuntimeDiagnosticsRequest](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-getruntimediagnosticsrequest): Queries bounded operational counters for the active host.
* [GetRuntimeDiagnosticsResponse](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-getruntimediagnosticsresponse): Returns bounded operational counters, independent of restricted evidence reads.
* [GuardrailDecision](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-guardraildecision): Explicit allow or nonempty block reason; missing selection is malformed.
* [HandshakeRequest](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-handshakerequest): Authenticates an activation and proposes the exact worker contract and plugin identity.
* [HandshakeResponse](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-handshakeresponse): Confirms worker identity, component multiplicity, and supported registration surfaces.
* [HealthRequest](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-healthrequest): Queries readiness using activation credentials; it may precede handshake.
* [HealthResponse](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-healthresponse): Reports readiness and worker identity without implying registration success.
* [ImageUrl](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-imageurl): Image URL and optional provider detail preference.
* [ImageUrlContentPart](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-imageurlcontentpart): Image URL input with portable URL options and provider extensions.
* [InspectDiagnosticMemoryRequest](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-inspectdiagnosticmemoryrequest): Requests memory evidence only under the activation's separately granted read authority.
* [InspectDiagnosticMemoryResponse](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-inspectdiagnosticmemoryresponse): Returns memory evidence or a portable domain read failure; transport failures use gRPC status.
* [InvokeRequest](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-invokerequest): Requires an invocation ID, a registration name, and one invocation alternative. The alternative must match the registered callback type. The request has no separate surface enum that could conflict with that alternative.
* [InvokeResponse](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-invokeresponse): One surface-specific success alternative or one callback/domain failure.
* [InvokeStreamRequest](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-invokestreamrequest): Streaming is a distinct method with a request-only codec context.
* [InvokeStreamResponse](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-invokestreamresponse): Exactly one item required. Error is terminal; clean EOF is successful closure.
* [JsonArray](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-jsonarray): Presence-bearing lists preserve None versus Some(\[]) in runtime DTOs.
* [JsonContentPart](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-jsoncontentpart): Provider-neutral image/audio/file payload with open provider fields.
* [JsonObject](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-jsonobject): Open object with structurally enforced string keys; each value is required.
* [JsonValue](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-jsonvalue): Exactly one UTF-8 RFC 8259 value, without NaN/Infinity or trailing content. Required payloads must contain bytes, including the bytes "null" for JSON null. Numbers are never converted through google.protobuf.Value/double.
* [ListRuntimeRegistrationsRequest](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-listruntimeregistrationsrequest): Lists runtime registrations, optionally restricted to selected surfaces.
* [ListRuntimeRegistrationsResponse](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-listruntimeregistrationsresponse): Returns the matching visible runtime registrations.
* [LlmCodecContext](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-llmcodeccontext): Codec reference and optional invocation-scoped host access capability.
* [LlmCodecReference](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-llmcodecreference): Uniform codec reference metadata, independent of implementation or provider. The host selects the actual codec through its invocation-scoped capability.
* [LlmConditionalInvocation](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-llmconditionalinvocation): Provider request supplied to an LLM execution condition.
* [LlmExecutionInvocation](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-llmexecutioninvocation): Unary LLM execution input with request and response codec access.
* [LlmMessage](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-llmmessage): The role is the alternative; contradictory roles cannot be represented.
* [LlmNextRequest](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-llmnextrequest): Invokes a live unary LLM continuation with a rewritten provider request.
* [LlmNextResponse](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-llmnextresponse): Selects the downstream provider response or its original domain failure.
* [LlmOptimizationContribution](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-llmoptimizationcontribution): Plugin-neutral optimization evidence with an open kind and optional custom payload.
* [LlmOptimizationModel](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-llmoptimizationmodel): Model and optional provider used in optimization accounting.
* [LlmOptimizationModelTransition](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-llmoptimizationmodeltransition): Optional baseline and effective model identities for an optimization.
* [LlmOptimizationSummary](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-llmoptimizationsummary): Host-computed optimization accounting at completed LLM scope closure.
* [LlmOptimizationTokenImpact](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-llmoptimizationtokenimpact): Baseline, effective, and saved token evidence with its quality and method.
* [LlmOptimizationTokens](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-llmoptimizationtokens): Optional token evidence; missing categories remain unknown rather than zero.
* [LlmRequest](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-llmrequest): Headers and content are required; content remains provider-owned JSON.
* [LlmRequestInterceptOutcome](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-llmrequestinterceptoutcome): Rewritten request, optional authoritative annotation, pending marks, and evidence.
* [LlmRequestInvocation](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-llmrequestinvocation): Request-interceptor input with optional normalized annotation.
* [LlmSanitizeRequestInvocation](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-llmsanitizerequestinvocation): Provider request and codec context supplied to an LLM request sanitizer.
* [LlmSanitizeResponseInvocation](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-llmsanitizeresponseinvocation): Provider response and codec context supplied to an LLM response sanitizer.
* [LlmStreamNextRequest](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-llmstreamnextrequest): Opens a live streaming LLM continuation with a rewritten provider request.
* [LlmStreamNextResponse](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-llmstreamnextresponse): One provider chunk or one terminal downstream domain failure.
* [LogRequest](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-logrequest): Submits an authenticated process-log record to the host-owned sink and threshold.
* [LogResponse](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-logresponse): Confirms the host accepted the log operation; failures use gRPC status.
* [MarkEvent](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-markevent): An ATOF point-in-time event with optional semantic categorization.
* [MemoryLimitEvent](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-memorylimitevent): Typed memory limit event preserving the shared runtime fields.
* [MemoryLimitEventSlot](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-memorylimiteventslot): One fixed resource limit-event slot, preserving the runtime's null positions.
* [MemorySelectionTotals](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-memoryselectiontotals): Typed memory selection totals preserving the shared runtime fields.
* [MessageContent](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-messagecontent): Selects plain text or a multimodal parts list, including explicit empty content.
* [NamedMessage](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-namedmessage): System, user, or developer message with required content and optional sender name.
* [OpenDiagnosticSessionRequest](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-opendiagnosticsessionrequest): Requests a session with exactly the diagnostic contracts advertised by the host.
* [OpenDiagnosticSessionResponse](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-opendiagnosticsessionresponse): Returns the activation's session identity and the confirmed host policy.
* [PendingMarkSpec](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-pendingmarkspec): Requests a mark whose UUID, timestamp, and parent are assigned by the host.
* [PluginRegistrationOwner](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-pluginregistrationowner): Identifies the plugin kind and optional component ordinal owning a registration.
* [PopScopeRequest](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-popscoperequest): Closes a previously pushed scope with optional output, metadata, and time.
* [PopScopeResponse](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-popscoperesponse): Confirms scope closure; failures use gRPC status.
* [ProtocolIdentity](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-protocolidentity): Protocol name nvidia.nemo.relay.worker.v1, contract version 1.0.0. Package/SDK releases are independent.
* [ProviderNativeComponent](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-providernativecomponent): Preserves provider-owned content with its provider and native discriminator.
* [PushScopeRequest](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-pushscoperequest): Creates and binds a scope under the selected parent context.
* [PushScopeResponse](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-pushscoperesponse): Returns the host-owned handle needed to close the newly pushed scope.
* [ReadDiagnosticPageRequest](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-readdiagnosticpagerequest): Requests snapshot evidence only under the activation's separately granted read authority.
* [ReadDiagnosticPageResponse](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-readdiagnosticpageresponse): Returns snapshot evidence or a portable domain read failure; transport failures use gRPC status.
* [RegisterConditionalMiddlewareGuardrailRequest](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-registerconditionalmiddlewareguardrailrequest): Installs an activation-owned conditional middleware guardrail.
* [RegisterConditionalMiddlewareGuardrailResponse](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-registerconditionalmiddlewareguardrailresponse): Returns the opaque handle for the newly installed conditional guardrail.
* [RegisterRequest](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-registerrequest): Registration is idempotent for the same semantic config within an activation. Concurrent repeats install once; changed config fails with FAILED_PRECONDITION.
* [RegisterResponse](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-registerresponse): Selects the installed registration plan or a registration callback failure.
* [Registration](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-registration): One callback's local identity, surface, priority, and chain behavior.
* [RegistrationPlan](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-registrationplan): Declarative callback and initial conditional-guardrail registrations for one component.
* [RemoteDiagnosticOrigin](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-remotediagnosticorigin): Preserves authenticated worker provenance and the host's receipt timing.
* [ResourceMemoryMeasurement](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-resourcememorymeasurement): Typed resource memory measurement preserving the shared runtime fields.
* [ResourceMemoryMetrics](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-resourcememorymetrics): Typed resource memory metrics preserving the shared runtime fields.
* [ResourceMemoryNumber](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-resourcememorynumber): Exact integer, finite decimal, or explicit non-finite collector result.
* [ResourceMemorySample](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-resourcememorysample): Typed resource memory sample preserving the shared runtime fields.
* [ResourceMemoryUnit](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-resourcememoryunit): Original measurement dimension and canonical unit, without conversion.
* [ResourceMemoryView](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-resourcememoryview): Typed resource memory view preserving the shared runtime fields.
* [ResourceProcessIdentity](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-resourceprocessidentity): Typed resource process identity preserving the shared runtime fields.
* [ResponseToolCall](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-responsetoolcall): Completed-response tool call with parsed JSON arguments.
* [ResponseToolCallList](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-responsetoolcalllist): Presence-bearing completed-response tool calls.
* [RuntimeDiagnostic](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-runtimediagnostic): One operational diagnostic code, safe description, and occurrence count.
* [RuntimeRegistrationIdentity](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-runtimeregistrationidentity): Describes local/effective callback identity, surface, and ownership.
* [RuntimeRegistrationOwner](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-runtimeregistrationowner): Selects core, global API, or plugin ownership of a runtime registration.
* [ScopeContext](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-scopecontext): Opaque host-issued stack/parent bindings, not public scope UUIDs.
* [ScopeEvent](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-scopeevent): An ATOF scope lifecycle event with an open semantic category.
* [ScopeStackEntry](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-scopestackentry): Owned public scope identity, distinct from an opaque host binding.
* [ScopeStackSnapshot](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-scopestacksnapshot): Owned scope identities ordered from root to the current top.
* [ShutdownRequest](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-shutdownrequest): Requests bounded worker drain and resource cleanup for the activation.
* [ShutdownResponse](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-shutdownresponse): Confirms successful admission of the worker shutdown request.
* [StringList](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-stringlist): Presence-bearing string list; a present empty list differs from absence.
* [SubmitDiagnosticRequest](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-submitdiagnosticrequest): Sends one ordered operation per request. Identical retries keep the sequence and content. A rejection before admission does not consume the sequence. An admitted policy rejection returns REJECTED and consumes the sequence. This service never retries execution callbacks.
* [SubmitDiagnosticResponse](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-submitdiagnosticresponse): Acknowledges one ordered diagnostic submission with its admission receipt.
* [TextContentPart](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-textcontentpart): Text or refusal content with provider-specific extension fields.
* [ToolCall](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-toolcall): Normalized request-side tool call; argument text remains provider-issued text.
* [ToolCallItem](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-toolcallitem): Portable top-level provider tool-call item with parsed arguments.
* [ToolCallList](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-toolcalllist): Presence-bearing tool-call list, preserving absent versus explicitly empty.
* [ToolChoice](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-toolchoice): Explicit automatic, disabled, required, named, or provider-native tool selection.
* [ToolChoiceFunction](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-toolchoicefunction): Provider function-choice discriminator and the selected function identity.
* [ToolChoiceFunctionName](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-toolchoicefunctionname): Identifies the function selected by a specific tool-choice rule.
* [ToolDefinition](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-tooldefinition): Selects a normalized function definition or a provider-native tool definition.
* [ToolDefinitionList](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-tooldefinitionlist): Presence-bearing tool-definition list, preserving absent versus explicitly empty.
* [ToolExecutionInterceptOutcome](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-toolexecutioninterceptoutcome): Canonical tool result plus ordered marks for host lifecycle materialization.
* [ToolExecutionInvocation](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-toolexecutioninvocation): Managed tool execution input and its invocation-scoped continuation.
* [ToolExecutionResult](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-toolexecutionresult): Application-visible tool result and optional opaque annotation.
* [ToolMessage](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-toolmessage): Tool result content correlated to a provider-issued tool call.
* [ToolNextRequest](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-toolnextrequest): Invokes a live tool continuation using a rewritten application value.
* [ToolNextResponse](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-toolnextresponse): Selects the downstream tool result or its original domain failure.
* [ToolResultContentPart](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-toolresultcontentpart): Tool result embedded in a provider content-block array.
* [ToolResultItem](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-toolresultitem): Portable top-level provider tool-result item with an open result payload.
* [ToolUseContentPart](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-toolusecontentpart): Tool invocation embedded in a provider content-block array.
* [ToolValueInvocation](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-toolvalueinvocation): Tool request/response value supplied to a sanitizer, condition, or request interceptor.
* [Usage](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-usage): Optional provider token counts and cost; absent counts never imply zero.
* [ValidateRequest](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-validaterequest): Validates one plugin configuration without installing callbacks.
* [ValidateResponse](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-validateresponse): Selects completed validation diagnostics or a validation callback failure.
* [WorkerError](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-workererror): Domain failure, never combined with a success value. RPC admission/auth/shape failures use gRPC status. Retryable never authorizes replay of execution.
* [WorkerIdentity](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-workeridentity): Worker, SDK, runtime, and protocol identities reported during activation.

## Enums

* [CapacityUnit](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/enum-capacityunit): Canonical capacity unit values from the shared runtime types.
* [ConfigDiagnosticLevel](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/enum-configdiagnosticlevel): Configuration diagnostic severity; unspecified is invalid for a reported diagnostic.
* [CostSource](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/enum-costsource): Origin of a cost value, separating pricing estimates from provider reports.
* [CountUnit](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/enum-countunit): Canonical count unit values from the shared runtime types.
* [DiagnosticAvailability](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/enum-diagnosticavailability): Availability of a diagnostic feature, window, or snapshot.
* [DiagnosticDomain](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/enum-diagnosticdomain): Canonical diagnostic domain values from the shared runtime types.
* [DiagnosticEvidenceRetention](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/enum-diagnosticevidenceretention): Evidence retention disposition, independent of occurrence accounting.
* [DiagnosticObservationOutcome](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/enum-diagnosticobservationoutcome): Observed operation outcome, independent of diagnostic severity.
* [DiagnosticObservationSeverity](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/enum-diagnosticobservationseverity): Evidence severity accepted by diagnostic delivery.
* [DiagnosticReadReason](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/enum-diagnosticreadreason): Canonical diagnostic read reason values from the shared runtime types.
* [DiagnosticReceiptStatus](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/enum-diagnosticreceiptstatus): Terminal admission outcome for an ordered diagnostic submission.
* [DiagnosticSummaryScope](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/enum-diagnosticsummaryscope): Aggregation scope of the reported lifetime summaries.
* [DurationUnit](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/enum-durationunit): Canonical duration unit values from the shared runtime types.
* [LlmOptimizationEvidenceQuality](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/enum-llmoptimizationevidencequality): Whether token evidence was observed or estimated.
* [LlmOptimizationSummaryStatus](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/enum-llmoptimizationsummarystatus): Whether optimization accounting is complete or limited by missing evidence.
* [LogSeverity](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/enum-logseverity): Log evidence severity; an unspecified submitted severity is invalid.
* [MemoryFieldScope](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/enum-memoryfieldscope): Canonical memory field scope values from the shared runtime types.
* [PluginDiagnosticFamily](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/enum-plugindiagnosticfamily): Canonical plugin diagnostic family values from the shared runtime types.
* [RegistrationSurface](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/enum-registrationsurface): Closed registration surfaces; unspecified and unknown values cannot be invoked.
* [ResourceAssociation](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/enum-resourceassociation): Canonical resource association values from the shared runtime types.
* [ResourceLimitEventKind](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/enum-resourcelimiteventkind): Canonical resource limit event kind values from the shared runtime types.
* [ResourceLimitResource](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/enum-resourcelimitresource): Canonical resource limit resource values from the shared runtime types.
* [ResourceMeasurementScope](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/enum-resourcemeasurementscope): Canonical resource measurement scope values from the shared runtime types.
* [ResourceMemoryAvailability](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/enum-resourcememoryavailability): Canonical resource memory availability values from the shared runtime types.
* [ResourceOperatingSystem](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/enum-resourceoperatingsystem): Canonical resource operating system values from the shared runtime types.
* [ResourceSampleStream](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/enum-resourcesamplestream): Canonical resource sample stream values from the shared runtime types.
* [ScopeCategory](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/enum-scopecategory): Scope lifecycle phase; unspecified is invalid for emitted scope events.
* [ScopeType](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/enum-scopetype): Recognized runtime scope types, including the explicit unknown-category fallback.
* [WorkerHealthStatus](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/enum-workerhealthstatus): Worker readiness state; unspecified is not a readiness assertion.

## Constants

* [CONTRACT_VERSION](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/constant-contract-version): Initial stable worker/schema contract baseline, independent of crate versions.
* [DIAGNOSTIC_PROVENANCE_CONTRACT_VERSION](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/constant-diagnostic-provenance-contract-version): Diagnostic provenance contract negotiated independently of the worker protocol.
* [DIAGNOSTIC_SNAPSHOT_CONTRACT_VERSION](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/constant-diagnostic-snapshot-contract-version): Diagnostic snapshot contract negotiated independently of the worker protocol.
* [WORKER_PROTOCOL](/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/constant-worker-protocol): Negotiation identifier for this contract, incompatible with legacy grpc-v1.

> Typed worker contract introduced alongside the legacy API.

## Docs

- [Module content_part](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/content_part.md): Nested message and enum types in `ContentPart`.
- [Enum Part](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/content_part/enum-part.md): Exactly one recognized alternative is required when this message is present.
- [Module decode_llm_codec_request_response](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/decode_llm_codec_request_response.md): Nested message and enum types in `DecodeLlmCodecRequestResponse`.
- [Enum Result](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/decode_llm_codec_request_response/enum-result.md): Exactly one recognized alternative is required when this message is present.
- [Module decode_llm_codec_response_response](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/decode_llm_codec_response_response.md): Nested message and enum types in `DecodeLlmCodecResponseResponse`.
- [Enum Result](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/decode_llm_codec_response_response/enum-result.md): Exactly one recognized alternative is required when this message is present.
- [Module diagnostic_code_definition](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/diagnostic_code_definition.md): Nested message and enum types in `DiagnosticCodeDefinition`.
- [Enum Definition](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/diagnostic_code_definition/enum-definition.md): Exactly one recognized alternative is required when this message is present.
- [Module encode_llm_codec_request_response](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/encode_llm_codec_request_response.md): Nested message and enum types in `EncodeLlmCodecRequestResponse`.
- [Enum Result](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/encode_llm_codec_request_response/enum-result.md): Exactly one recognized alternative is required when this message is present.
- [Module event](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/event.md): Nested message and enum types in `Event`.
- [Enum Kind](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/event/enum-kind.md): Exactly one recognized alternative is required when this message is present.
- [Module finish_reason](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/finish_reason.md): Nested message and enum types in `FinishReason`.
- [Enum Reason](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/finish_reason/enum-reason.md): Exactly one recognized alternative is required when this message is present.
- [Module get_current_scope_stack_snapshot_response](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/get_current_scope_stack_snapshot_response.md): Nested message and enum types in `GetCurrentScopeStackSnapshotResponse`.
- [Enum Result](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/get_current_scope_stack_snapshot_response/enum-result.md): Exactly one recognized alternative is required when this message is present.
- [Module get_diagnostic_discovery_response](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/get_diagnostic_discovery_response.md): Nested message and enum types in `GetDiagnosticDiscoveryResponse`.
- [Enum Result](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/get_diagnostic_discovery_response/enum-result.md): Exactly one result is required; a failed read must not look like empty evidence.
- [Module guardrail_decision](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/guardrail_decision.md): Nested message and enum types in `GuardrailDecision`.
- [Enum Decision](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/guardrail_decision/enum-decision.md): Exactly one recognized alternative is required when this message is present.
- [Module inspect_diagnostic_memory_response](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/inspect_diagnostic_memory_response.md): Nested message and enum types in `InspectDiagnosticMemoryResponse`.
- [Enum Result](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/inspect_diagnostic_memory_response/enum-result.md): Exactly one result is required; a failed read must not look like empty evidence.
- [Module invoke_request](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/invoke_request.md): Nested message and enum types in `InvokeRequest`.
- [Enum Invocation](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/invoke_request/enum-invocation.md): Exactly one recognized alternative is required when this message is present.
- [Module invoke_response](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/invoke_response.md): Nested message and enum types in `InvokeResponse`.
- [Enum Result](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/invoke_response/enum-result.md): Exactly one recognized alternative is required when this message is present.
- [Module invoke_stream_response](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/invoke_stream_response.md): Nested message and enum types in `InvokeStreamResponse`.
- [Enum Item](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/invoke_stream_response/enum-item.md): Exactly one recognized alternative is required when this message is present.
- [Module llm_message](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/llm_message.md): Nested message and enum types in `LlmMessage`.
- [Enum Role](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/llm_message/enum-role.md): Exactly one recognized alternative is required when this message is present.
- [Module llm_next_response](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/llm_next_response.md): Nested message and enum types in `LlmNextResponse`.
- [Enum Result](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/llm_next_response/enum-result.md): Exactly one recognized alternative is required when this message is present.
- [Module llm_stream_next_response](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/llm_stream_next_response.md): Nested message and enum types in `LlmStreamNextResponse`.
- [Enum Item](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/llm_stream_next_response/enum-item.md): Exactly one recognized alternative is required when this message is present.
- [Module memory_limit_event_slot](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/memory_limit_event_slot.md): Nested message and enum types in `MemoryLimitEventSlot`.
- [Enum State](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/memory_limit_event_slot/enum-state.md): Exactly one present or absent slot selection is required.
- [Module message_content](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/message_content.md): Nested message and enum types in `MessageContent`.
- [Enum Content](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/message_content/enum-content.md): Exactly one recognized alternative is required when this message is present.
- [Module plugin_worker_service_client](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/plugin_worker_service_client.md): Generated client implementations.
- [Struct Plugin Worker Service Client](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/plugin_worker_service_client/struct-pluginworkerserviceclient.md): nvidia.nemo.relay.worker.v1@1.0.0. Authentication, malformed input, and incompatible identity use gRPC status. Callback/domain errors use the response's single result oneof.
- [Module plugin_worker_service_server](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/plugin_worker_service_server.md): Generated server implementations.
- [Struct Plugin Worker Service Server](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/plugin_worker_service_server/struct-pluginworkerserviceserver.md): nvidia.nemo.relay.worker.v1@1.0.0. Authentication, malformed input, and incompatible identity use gRPC status. Callback/domain errors use the response's single result oneof.
- [Constant SERVICE_NAME](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/plugin_worker_service_server/constant-service-name.md): Generated gRPC service name
- [Trait Plugin Worker Service](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/plugin_worker_service_server/trait-pluginworkerservice.md): Generated trait containing gRPC methods that should be implemented for use with PluginWorkerServiceServer.
- [Module read_diagnostic_page_response](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/read_diagnostic_page_response.md): Nested message and enum types in `ReadDiagnosticPageResponse`.
- [Enum Result](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/read_diagnostic_page_response/enum-result.md): Exactly one result is required; a failed read must not look like empty evidence.
- [Module register_response](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/register_response.md): Nested message and enum types in `RegisterResponse`.
- [Enum Result](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/register_response/enum-result.md): Exactly one recognized alternative is required when this message is present.
- [Module relay_diagnostics_service_client](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/relay_diagnostics_service_client.md): Generated client implementations.
- [Struct Relay Diagnostics Service Client](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/relay_diagnostics_service_client/struct-relaydiagnosticsserviceclient.md): Diagnostic admission, limits, retry policy, and read authorization are separate from execution. ReadDiagnosticPage is denied unless explicit authority exists.
- [Module relay_diagnostics_service_server](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/relay_diagnostics_service_server.md): Generated server implementations.
- [Struct Relay Diagnostics Service Server](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/relay_diagnostics_service_server/struct-relaydiagnosticsserviceserver.md): Diagnostic admission, limits, retry policy, and read authorization are separate from execution. ReadDiagnosticPage is denied unless explicit authority exists.
- [Constant SERVICE_NAME](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/relay_diagnostics_service_server/constant-service-name.md): Generated gRPC service name
- [Trait Relay Diagnostics Service](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/relay_diagnostics_service_server/trait-relaydiagnosticsservice.md): Generated trait containing gRPC methods that should be implemented for use with RelayDiagnosticsServiceServer.
- [Module relay_host_runtime_service_client](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/relay_host_runtime_service_client.md): Generated client implementations.
- [Struct Relay Host Runtime Service Client](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/relay_host_runtime_service_client/struct-relayhostruntimeserviceclient.md): Authenticated host runtime operations for scope, continuation, codec, and registration access.
- [Module relay_host_runtime_service_server](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/relay_host_runtime_service_server.md): Generated server implementations.
- [Struct Relay Host Runtime Service Server](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/relay_host_runtime_service_server/struct-relayhostruntimeserviceserver.md): Authenticated host runtime operations for scope, continuation, codec, and registration access.
- [Constant SERVICE_NAME](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/relay_host_runtime_service_server/constant-service-name.md): Generated gRPC service name
- [Trait Relay Host Runtime Service](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/relay_host_runtime_service_server/trait-relayhostruntimeservice.md): Generated trait containing gRPC methods that should be implemented for use with RelayHostRuntimeServiceServer.
- [Module resource_memory_number](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/resource_memory_number.md): Nested message and enum types in `ResourceMemoryNumber`.
- [Enum Kind](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/resource_memory_number/enum-kind.md): Exactly one original numeric kind is required.
- [Module resource_memory_unit](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/resource_memory_unit.md): Nested message and enum types in `ResourceMemoryUnit`.
- [Enum Dimension](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/resource_memory_unit/enum-dimension.md): Exactly one original unit family is required.
- [Module runtime_registration_owner](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/runtime_registration_owner.md): Nested message and enum types in `RuntimeRegistrationOwner`.
- [Enum Owner](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/runtime_registration_owner/enum-owner.md): Exactly one recognized alternative is required when this message is present.
- [Module submit_diagnostic_request](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/submit_diagnostic_request.md): Nested message and enum types in `SubmitDiagnosticRequest`.
- [Enum Operation](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/submit_diagnostic_request/enum-operation.md): Exactly one recognized alternative is required when this message is present.
- [Module tool_choice](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/tool_choice.md): Nested message and enum types in `ToolChoice`.
- [Enum Choice](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/tool_choice/enum-choice.md): Exactly one recognized alternative is required when this message is present.
- [Module tool_definition](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/tool_definition.md): Nested message and enum types in `ToolDefinition`.
- [Enum Definition](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/tool_definition/enum-definition.md): Exactly one recognized alternative is required when this message is present.
- [Module tool_next_response](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/tool_next_response.md): Nested message and enum types in `ToolNextResponse`.
- [Enum Result](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/tool_next_response/enum-result.md): Exactly one recognized alternative is required when this message is present.
- [Module validate_response](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/validate_response.md): Nested message and enum types in `ValidateResponse`.
- [Enum Result](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/validate_response/enum-result.md): Exactly one recognized alternative is required when this message is present.
- [Struct Annotated LlmRequest](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-annotatedllmrequest.md): Normalized request structure with explicit provider-specific and extension fields.
- [Struct Annotated LlmResponse](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-annotatedllmresponse.md): Normalized completed response, usage, pricing, and optimization evidence.
- [Struct Assistant Message](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-assistantmessage.md): Assistant output with independently optional content and tool calls.
- [Struct Base Event](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-baseevent.md): Common ATOF identity, propagation, timing, and application payload fields.
- [Struct Cache Write Token Counts](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-cachewritetokencounts.md): Prompt-cache write tokens retained for one cache duration.
- [Struct Cache Write Token Counts List](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-cachewritetokencountslist.md): Presence-bearing duration-aware prompt-cache write counts.
- [Struct Cancel Invocation Request](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-cancelinvocationrequest.md): Requests cancellation of one active invocation without replaying work.
- [Struct Cancel Invocation Response](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-cancelinvocationresponse.md): Idempotent: unknown/completed IDs return accepted=false, without resurrecting work.
- [Struct Category Profile](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-categoryprofile.md): Known category-specific fields and lossless extensions attached to an event.
- [Struct Component Memory Footprint](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-componentmemoryfootprint.md): Typed component memory footprint preserving the shared runtime fields.
- [Struct Component Memory Usage](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-componentmemoryusage.md): Typed component memory usage preserving the shared runtime fields.
- [Struct Conditional Middleware Guardrail Registration](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-conditionalmiddlewareguardrailregistration.md): Declares a static or callback-based filter over runtime registrations.
- [Struct Conditional Middleware Invocation](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-conditionalmiddlewareinvocation.md): Asks a conditional callback whether selected middleware registrations may execute.
- [Struct Config Diagnostic](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-configdiagnostic.md): Structured configuration warning or error with optional component and field location.
- [Struct Config Diagnostics](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-configdiagnostics.md): Present validation result; an empty list is successful validation without diagnostics.
- [Struct Content Part](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-contentpart.md): Selects a normalized content block or a lossless provider-native block.
- [Struct Content Part List](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-contentpartlist.md): Ordered multimodal content; a present empty list remains an explicit variant.
- [Struct Cost Estimate](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-costestimate.md): Normalized monetary cost with provenance for estimates and provider-reported values.
- [Struct Create Scope Stack Request](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-createscopestackrequest.md): Creates an isolated host-owned scope stack for this activation.
- [Struct Create Scope Stack Response](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-createscopestackresponse.md): Returns the new isolated stack's opaque binding identity.
- [Struct Credentials](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-credentials.md): Required on authenticated requests. Both strings must match the activation.
- [Struct Data Schema](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-dataschema.md): Application-owned schema identity; its version is not the worker version.
- [Struct Decode LlmCodec Request Request](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-decodellmcodecrequestrequest.md): Requests normalized decoding through an invocation-bound request codec.
- [Struct Decode LlmCodec Request Response](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-decodellmcodecrequestresponse.md): Selects the normalized request or the codec's domain failure.
- [Struct Decode LlmCodec Response Request](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-decodellmcodecresponserequest.md): Requests normalized decoding through an invocation-bound response codec.
- [Struct Decode LlmCodec Response Response](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-decodellmcodecresponseresponse.md): Selects the normalized completed response or the codec's domain failure.
- [Struct Deregister Conditional Middleware Guardrail Request](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-deregisterconditionalmiddlewareguardrailrequest.md): Removes a conditional guardrail using its activation-owned handle.
- [Struct Deregister Conditional Middleware Guardrail Response](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-deregisterconditionalmiddlewareguardrailresponse.md): Reports whether an owned conditional guardrail was removed.
- [Struct Diagnostic Capabilities](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-diagnosticcapabilities.md): Host-owned limits and contract identities required for diagnostic admission.
- [Struct Diagnostic Capability](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-diagnosticcapability.md): Availability and optional reason for one named diagnostic feature.
- [Struct Diagnostic Classification](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-diagnosticclassification.md): Preserves catalogue and failure-class names, including unknown future names.
- [Struct Diagnostic Code Definition](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-diagnosticcodedefinition.md): Selects an existing catalogue name or an activation-local extension definition.
- [Struct Diagnostic Component Close](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-diagnosticcomponentclose.md): Closes a component handle without deleting its retained accounting.
- [Struct Diagnostic Component Identity](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-diagnosticcomponentidentity.md): Identifies a logical component and one registration incarnation.
- [Struct Diagnostic Component Ownership](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-diagnosticcomponentownership.md): Correlates component responsibility without creating additional counter dimensions.
- [Struct Diagnostic Component Registration](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-diagnosticcomponentregistration.md): Registers a bounded diagnostic component and an ordered list of code handles.
- [Struct Diagnostic Component Snapshot](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-diagnosticcomponentsnapshot.md): A retained component row with lifetime, refresh, counters, and windows.
- [Struct Diagnostic Correlation](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-diagnosticcorrelation.md): Optional trajectory correlation, excluded from aggregation keys.
- [Struct Diagnostic Count](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-diagnosticcount.md): Unsigned count that stops at its maximum. After that limit, it is a lower bound.
- [Struct Diagnostic Counter](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-diagnosticcounter.md): Lifetime occurrence count and latest observation time for one admitted code.
- [Struct Diagnostic Coverage](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-diagnosticcoverage.md): Describes snapshot availability, aggregation scope, retention, and evidence loss.
- [Struct Diagnostic Cursor](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-diagnosticcursor.md): Canonical snapshot position; it does not grant transport read authority.
- [Struct Diagnostic Detail](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-diagnosticdetail.md): Retained diagnostic text with explicit truncation state.
- [Struct Diagnostic Discovery](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-diagnosticdiscovery.md): Typed diagnostic discovery preserving the shared runtime fields.
- [Struct Diagnostic Event](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-diagnosticevent.md): One retained observation, its attribution, occurrence delta, and optional evidence.
- [Struct Diagnostic Extension Definition](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-diagnosticextensiondefinition.md): Declares one plugin-defined diagnostic classification and its allowed causes.
- [Struct Diagnostic Lifetime Summary](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-diagnosticlifetimesummary.md): Lifetime totals and monotonic elapsed time for a source or component.
- [Struct Diagnostic Loss](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-diagnosticloss.md): Explicit counters for bounded-storage, admission, and projection losses.
- [Struct Diagnostic Memory Page](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-diagnosticmemorypage.md): Typed diagnostic memory page preserving the shared runtime fields.
- [Struct Diagnostic Memory Usage](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-diagnosticmemoryusage.md): Typed diagnostic memory usage preserving the shared runtime fields.
- [Struct Diagnostic Observation](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-diagnosticobservation.md): Records a positive occurrence delta using admitted component and code handles.
- [Struct Diagnostic Origin](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-diagnosticorigin.md): Captures the refresh generation and ownership at observation time.
- [Struct Diagnostic Plugin Context](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-diagnosticplugincontext.md): Carries independently optional plugin execution and lifecycle phase names.
- [Struct Diagnostic Producer Support](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-diagnosticproducersupport.md): Typed diagnostic producer support preserving the shared runtime fields.
- [Struct Diagnostic Query](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-diagnosticquery.md): Typed diagnostic query preserving the shared runtime fields.
- [Struct Diagnostic Receipt](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-diagnosticreceipt.md): Reports sequence consumption, admission outcome, and retained evidence disposition.
- [Struct Diagnostic Refresh Summary](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-diagnosticrefreshsummary.md): Accounting for the component's current refresh generation and ownership.
- [Struct Diagnostic Retention](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-diagnosticretention.md): Reports retained bounds and whether the requested page was truncated.
- [Struct Diagnostic Snapshot](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-diagnosticsnapshot.md): JSON output represents every uint64 diagnostic counter as a decimal string.
- [Struct Diagnostic Source Identity](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-diagnosticsourceidentity.md): Identifies the process incarnation that owns diagnostic accounting.
- [Struct Diagnostic Totals](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-diagnostictotals.md): Outcome and recording totals for an explicitly identified accounting scope.
- [Struct Diagnostic Window](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-diagnosticwindow.md): Bounded outcome history at one configured time resolution.
- [Struct Diagnostic Window Bucket](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-diagnosticwindowbucket.md): Outcome counts for one source-local elapsed-time interval.
- [Struct Diagnostic Window Coverage](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-diagnosticwindowcoverage.md): Reports the temporal extent and completeness of a diagnostic window.
- [Struct Drop Scope Stack Request](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-dropscopestackrequest.md): Releases an activation-owned isolated scope stack.
- [Struct Drop Scope Stack Response](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-dropscopestackresponse.md): Confirms stack release; failures use gRPC status.
- [Struct Emit Mark Request](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-emitmarkrequest.md): Requests host materialization of a mark in the selected scope context.
- [Struct Emit Mark Response](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-emitmarkresponse.md): Confirms the mark operation completed; failures use gRPC status.
- [Struct Encode LlmCodec Request Request](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-encodellmcodecrequestrequest.md): Requests provider encoding from an annotation and original request baseline.
- [Struct Encode LlmCodec Request Response](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-encodellmcodecrequestresponse.md): Selects the encoded provider request or the codec's domain failure.
- [Struct Entry Memory Footprint](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-entrymemoryfootprint.md): Typed entry memory footprint preserving the shared runtime fields.
- [Struct Entry Memory Usage](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-entrymemoryusage.md): Typed entry memory usage preserving the shared runtime fields.
- [Struct Event](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-event.md): Exactly one kind is required. UUID strings use canonical hyphenated UUIDs.
- [Struct Event Sanitize Fields](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-eventsanitizefields.md): Sanitizer output replaces these fields; absence clears the corresponding field.
- [Struct Finish Reason](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-finishreason.md): Normalized completion reason with an explicit lossless unknown-name alternative.
- [Struct Function Call](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-functioncall.md): Function name and original argument text, which need not be complete JSON.
- [Struct Function Definition](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-functiondefinition.md): Function name, optional description and JSON Schema, strictness, and extensions.
- [Struct Function Message](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-functionmessage.md): Legacy function result; absent content represents explicit null in the runtime DTO.
- [Struct Function Tool Definition](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-functiontooldefinition.md): Function tool definition plus provider fields outside the normalized function.
- [Struct Generation Params](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-generationparams.md): Portable generation controls with presence preserved for every optional value.
- [Struct GetCurrent Scope Stack Snapshot Request](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-getcurrentscopestacksnapshotrequest.md): Queries the scope stack bound to an invocation or selected scope context.
- [Struct GetCurrent Scope Stack Snapshot Response](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-getcurrentscopestacksnapshotresponse.md): Selects a present snapshot or an explicit absence of bound context.
- [Struct GetDiagnostic Capabilities Request](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-getdiagnosticcapabilitiesrequest.md): Queries diagnostic policy using activation credentials, without opening a session.
- [Struct GetDiagnostic Capabilities Response](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-getdiagnosticcapabilitiesresponse.md): Returns the host's bounded diagnostic delivery and read policy.
- [Struct GetDiagnostic Discovery Request](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-getdiagnosticdiscoveryrequest.md): Requests discovery evidence only under the activation's separately granted read authority.
- [Struct GetDiagnostic Discovery Response](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-getdiagnosticdiscoveryresponse.md): Returns discovery evidence or a portable domain read failure; transport failures use gRPC status.
- [Struct GetRuntime Diagnostics Request](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-getruntimediagnosticsrequest.md): Queries bounded operational counters for the active host.
- [Struct GetRuntime Diagnostics Response](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-getruntimediagnosticsresponse.md): Returns bounded operational counters, independent of restricted evidence reads.
- [Struct Guardrail Decision](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-guardraildecision.md): Explicit allow or nonempty block reason; missing selection is malformed.
- [Struct Handshake Request](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-handshakerequest.md): Authenticates an activation and proposes the exact worker contract and plugin identity.
- [Struct Handshake Response](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-handshakeresponse.md): Confirms worker identity, component multiplicity, and supported registration surfaces.
- [Struct Health Request](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-healthrequest.md): Queries readiness using activation credentials; it may precede handshake.
- [Struct Health Response](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-healthresponse.md): Reports readiness and worker identity without implying registration success.
- [Struct Image Url](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-imageurl.md): Image URL and optional provider detail preference.
- [Struct Image UrlContent Part](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-imageurlcontentpart.md): Image URL input with portable URL options and provider extensions.
- [Struct Inspect Diagnostic Memory Request](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-inspectdiagnosticmemoryrequest.md): Requests memory evidence only under the activation's separately granted read authority.
- [Struct Inspect Diagnostic Memory Response](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-inspectdiagnosticmemoryresponse.md): Returns memory evidence or a portable domain read failure; transport failures use gRPC status.
- [Struct Invoke Request](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-invokerequest.md): Requires an invocation ID, a registration name, and one invocation alternative. The alternative must match the registered callback type. The request has no separate surface enum that could conflict with that alternative.
- [Struct Invoke Response](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-invokeresponse.md): One surface-specific success alternative or one callback/domain failure.
- [Struct Invoke Stream Request](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-invokestreamrequest.md): Streaming is a distinct method with a request-only codec context.
- [Struct Invoke Stream Response](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-invokestreamresponse.md): Exactly one item required. Error is terminal; clean EOF is successful closure.
- [Struct Json Array](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-jsonarray.md): Presence-bearing lists preserve None versus Some([]) in runtime DTOs.
- [Struct Json Content Part](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-jsoncontentpart.md): Provider-neutral image/audio/file payload with open provider fields.
- [Struct Json Object](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-jsonobject.md): Open object with structurally enforced string keys; each value is required.
- [Struct Json Value](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-jsonvalue.md): Exactly one UTF-8 RFC 8259 value, without NaN/Infinity or trailing content. Required payloads must contain bytes, including the bytes "null" for JSON null. Numbers are never converted through google.protobuf.Value/double.
- [Struct List Runtime Registrations Request](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-listruntimeregistrationsrequest.md): Lists runtime registrations, optionally restricted to selected surfaces.
- [Struct List Runtime Registrations Response](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-listruntimeregistrationsresponse.md): Returns the matching visible runtime registrations.
- [Struct LlmCodec Context](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-llmcodeccontext.md): Codec reference and optional invocation-scoped host access capability.
- [Struct LlmCodec Reference](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-llmcodecreference.md): Uniform codec reference metadata, independent of implementation or provider. The host selects the actual codec through its invocation-scoped capability.
- [Struct LlmConditional Invocation](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-llmconditionalinvocation.md): Provider request supplied to an LLM execution condition.
- [Struct LlmExecution Invocation](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-llmexecutioninvocation.md): Unary LLM execution input with request and response codec access.
- [Struct LlmMessage](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-llmmessage.md): The role is the alternative; contradictory roles cannot be represented.
- [Struct LlmNext Request](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-llmnextrequest.md): Invokes a live unary LLM continuation with a rewritten provider request.
- [Struct LlmNext Response](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-llmnextresponse.md): Selects the downstream provider response or its original domain failure.
- [Struct LlmOptimization Contribution](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-llmoptimizationcontribution.md): Plugin-neutral optimization evidence with an open kind and optional custom payload.
- [Struct LlmOptimization Model](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-llmoptimizationmodel.md): Model and optional provider used in optimization accounting.
- [Struct LlmOptimization Model Transition](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-llmoptimizationmodeltransition.md): Optional baseline and effective model identities for an optimization.
- [Struct LlmOptimization Summary](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-llmoptimizationsummary.md): Host-computed optimization accounting at completed LLM scope closure.
- [Struct LlmOptimization Token Impact](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-llmoptimizationtokenimpact.md): Baseline, effective, and saved token evidence with its quality and method.
- [Struct LlmOptimization Tokens](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-llmoptimizationtokens.md): Optional token evidence; missing categories remain unknown rather than zero.
- [Struct LlmRequest](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-llmrequest.md): Headers and content are required; content remains provider-owned JSON.
- [Struct LlmRequest Intercept Outcome](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-llmrequestinterceptoutcome.md): Rewritten request, optional authoritative annotation, pending marks, and evidence.
- [Struct LlmRequest Invocation](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-llmrequestinvocation.md): Request-interceptor input with optional normalized annotation.
- [Struct LlmSanitize Request Invocation](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-llmsanitizerequestinvocation.md): Provider request and codec context supplied to an LLM request sanitizer.
- [Struct LlmSanitize Response Invocation](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-llmsanitizeresponseinvocation.md): Provider response and codec context supplied to an LLM response sanitizer.
- [Struct LlmStream Next Request](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-llmstreamnextrequest.md): Opens a live streaming LLM continuation with a rewritten provider request.
- [Struct LlmStream Next Response](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-llmstreamnextresponse.md): One provider chunk or one terminal downstream domain failure.
- [Struct LogRequest](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-logrequest.md): Submits an authenticated process-log record to the host-owned sink and threshold.
- [Struct LogResponse](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-logresponse.md): Confirms the host accepted the log operation; failures use gRPC status.
- [Struct Mark Event](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-markevent.md): An ATOF point-in-time event with optional semantic categorization.
- [Struct Memory Limit Event](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-memorylimitevent.md): Typed memory limit event preserving the shared runtime fields.
- [Struct Memory Limit Event Slot](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-memorylimiteventslot.md): One fixed resource limit-event slot, preserving the runtime's null positions.
- [Struct Memory Selection Totals](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-memoryselectiontotals.md): Typed memory selection totals preserving the shared runtime fields.
- [Struct Message Content](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-messagecontent.md): Selects plain text or a multimodal parts list, including explicit empty content.
- [Struct Named Message](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-namedmessage.md): System, user, or developer message with required content and optional sender name.
- [Struct Open Diagnostic Session Request](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-opendiagnosticsessionrequest.md): Requests a session with exactly the diagnostic contracts advertised by the host.
- [Struct Open Diagnostic Session Response](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-opendiagnosticsessionresponse.md): Returns the activation's session identity and the confirmed host policy.
- [Struct Pending Mark Spec](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-pendingmarkspec.md): Requests a mark whose UUID, timestamp, and parent are assigned by the host.
- [Struct Plugin Registration Owner](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-pluginregistrationowner.md): Identifies the plugin kind and optional component ordinal owning a registration.
- [Struct PopScope Request](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-popscoperequest.md): Closes a previously pushed scope with optional output, metadata, and time.
- [Struct PopScope Response](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-popscoperesponse.md): Confirms scope closure; failures use gRPC status.
- [Struct Protocol Identity](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-protocolidentity.md): Protocol name nvidia.nemo.relay.worker.v1, contract version 1.0.0. Package/SDK releases are independent.
- [Struct Provider Native Component](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-providernativecomponent.md): Preserves provider-owned content with its provider and native discriminator.
- [Struct Push Scope Request](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-pushscoperequest.md): Creates and binds a scope under the selected parent context.
- [Struct Push Scope Response](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-pushscoperesponse.md): Returns the host-owned handle needed to close the newly pushed scope.
- [Struct Read Diagnostic Page Request](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-readdiagnosticpagerequest.md): Requests snapshot evidence only under the activation's separately granted read authority.
- [Struct Read Diagnostic Page Response](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-readdiagnosticpageresponse.md): Returns snapshot evidence or a portable domain read failure; transport failures use gRPC status.
- [Struct Register Conditional Middleware Guardrail Request](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-registerconditionalmiddlewareguardrailrequest.md): Installs an activation-owned conditional middleware guardrail.
- [Struct Register Conditional Middleware Guardrail Response](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-registerconditionalmiddlewareguardrailresponse.md): Returns the opaque handle for the newly installed conditional guardrail.
- [Struct Register Request](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-registerrequest.md): Registration is idempotent for the same semantic config within an activation. Concurrent repeats install once; changed config fails with FAILED_PRECONDITION.
- [Struct Register Response](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-registerresponse.md): Selects the installed registration plan or a registration callback failure.
- [Struct Registration](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-registration.md): One callback's local identity, surface, priority, and chain behavior.
- [Struct Registration Plan](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-registrationplan.md): Declarative callback and initial conditional-guardrail registrations for one component.
- [Struct Remote Diagnostic Origin](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-remotediagnosticorigin.md): Preserves authenticated worker provenance and the host's receipt timing.
- [Struct Resource Memory Measurement](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-resourcememorymeasurement.md): Typed resource memory measurement preserving the shared runtime fields.
- [Struct Resource Memory Metrics](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-resourcememorymetrics.md): Typed resource memory metrics preserving the shared runtime fields.
- [Struct Resource Memory Number](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-resourcememorynumber.md): Exact integer, finite decimal, or explicit non-finite collector result.
- [Struct Resource Memory Sample](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-resourcememorysample.md): Typed resource memory sample preserving the shared runtime fields.
- [Struct Resource Memory Unit](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-resourcememoryunit.md): Original measurement dimension and canonical unit, without conversion.
- [Struct Resource Memory View](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-resourcememoryview.md): Typed resource memory view preserving the shared runtime fields.
- [Struct Resource Process Identity](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-resourceprocessidentity.md): Typed resource process identity preserving the shared runtime fields.
- [Struct Response Tool Call](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-responsetoolcall.md): Completed-response tool call with parsed JSON arguments.
- [Struct Response Tool Call List](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-responsetoolcalllist.md): Presence-bearing completed-response tool calls.
- [Struct Runtime Diagnostic](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-runtimediagnostic.md): One operational diagnostic code, safe description, and occurrence count.
- [Struct Runtime Registration Identity](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-runtimeregistrationidentity.md): Describes local/effective callback identity, surface, and ownership.
- [Struct Runtime Registration Owner](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-runtimeregistrationowner.md): Selects core, global API, or plugin ownership of a runtime registration.
- [Struct Scope Context](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-scopecontext.md): Opaque host-issued stack/parent bindings, not public scope UUIDs.
- [Struct Scope Event](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-scopeevent.md): An ATOF scope lifecycle event with an open semantic category.
- [Struct Scope Stack Entry](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-scopestackentry.md): Owned public scope identity, distinct from an opaque host binding.
- [Struct Scope Stack Snapshot](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-scopestacksnapshot.md): Owned scope identities ordered from root to the current top.
- [Struct Shutdown Request](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-shutdownrequest.md): Requests bounded worker drain and resource cleanup for the activation.
- [Struct Shutdown Response](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-shutdownresponse.md): Confirms successful admission of the worker shutdown request.
- [Struct String List](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-stringlist.md): Presence-bearing string list; a present empty list differs from absence.
- [Struct Submit Diagnostic Request](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-submitdiagnosticrequest.md): Sends one ordered operation per request. Identical retries keep the sequence and content. A rejection before admission does not consume the sequence. An admitted policy rejection returns REJECTED and consumes the sequence. This service never retries execution callbacks.
- [Struct Submit Diagnostic Response](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-submitdiagnosticresponse.md): Acknowledges one ordered diagnostic submission with its admission receipt.
- [Struct Text Content Part](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-textcontentpart.md): Text or refusal content with provider-specific extension fields.
- [Struct Tool Call](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-toolcall.md): Normalized request-side tool call; argument text remains provider-issued text.
- [Struct Tool Call Item](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-toolcallitem.md): Portable top-level provider tool-call item with parsed arguments.
- [Struct Tool Call List](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-toolcalllist.md): Presence-bearing tool-call list, preserving absent versus explicitly empty.
- [Struct Tool Choice](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-toolchoice.md): Explicit automatic, disabled, required, named, or provider-native tool selection.
- [Struct Tool Choice Function](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-toolchoicefunction.md): Provider function-choice discriminator and the selected function identity.
- [Struct Tool Choice Function Name](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-toolchoicefunctionname.md): Identifies the function selected by a specific tool-choice rule.
- [Struct Tool Definition](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-tooldefinition.md): Selects a normalized function definition or a provider-native tool definition.
- [Struct Tool Definition List](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-tooldefinitionlist.md): Presence-bearing tool-definition list, preserving absent versus explicitly empty.
- [Struct Tool Execution Intercept Outcome](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-toolexecutioninterceptoutcome.md): Canonical tool result plus ordered marks for host lifecycle materialization.
- [Struct Tool Execution Invocation](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-toolexecutioninvocation.md): Managed tool execution input and its invocation-scoped continuation.
- [Struct Tool Execution Result](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-toolexecutionresult.md): Application-visible tool result and optional opaque annotation.
- [Struct Tool Message](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-toolmessage.md): Tool result content correlated to a provider-issued tool call.
- [Struct Tool Next Request](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-toolnextrequest.md): Invokes a live tool continuation using a rewritten application value.
- [Struct Tool Next Response](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-toolnextresponse.md): Selects the downstream tool result or its original domain failure.
- [Struct Tool Result Content Part](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-toolresultcontentpart.md): Tool result embedded in a provider content-block array.
- [Struct Tool Result Item](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-toolresultitem.md): Portable top-level provider tool-result item with an open result payload.
- [Struct Tool UseContent Part](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-toolusecontentpart.md): Tool invocation embedded in a provider content-block array.
- [Struct Tool Value Invocation](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-toolvalueinvocation.md): Tool request/response value supplied to a sanitizer, condition, or request interceptor.
- [Struct Usage](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-usage.md): Optional provider token counts and cost; absent counts never imply zero.
- [Struct Validate Request](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-validaterequest.md): Validates one plugin configuration without installing callbacks.
- [Struct Validate Response](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-validateresponse.md): Selects completed validation diagnostics or a validation callback failure.
- [Struct Worker Error](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-workererror.md): Domain failure, never combined with a success value. RPC admission/auth/shape failures use gRPC status. Retryable never authorizes replay of execution.
- [Struct Worker Identity](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/struct-workeridentity.md): Worker, SDK, runtime, and protocol identities reported during activation.
- [Enum Capacity Unit](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/enum-capacityunit.md): Canonical capacity unit values from the shared runtime types.
- [Enum Config Diagnostic Level](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/enum-configdiagnosticlevel.md): Configuration diagnostic severity; unspecified is invalid for a reported diagnostic.
- [Enum Cost Source](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/enum-costsource.md): Origin of a cost value, separating pricing estimates from provider reports.
- [Enum Count Unit](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/enum-countunit.md): Canonical count unit values from the shared runtime types.
- [Enum Diagnostic Availability](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/enum-diagnosticavailability.md): Availability of a diagnostic feature, window, or snapshot.
- [Enum Diagnostic Domain](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/enum-diagnosticdomain.md): Canonical diagnostic domain values from the shared runtime types.
- [Enum Diagnostic Evidence Retention](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/enum-diagnosticevidenceretention.md): Evidence retention disposition, independent of occurrence accounting.
- [Enum Diagnostic Observation Outcome](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/enum-diagnosticobservationoutcome.md): Observed operation outcome, independent of diagnostic severity.
- [Enum Diagnostic Observation Severity](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/enum-diagnosticobservationseverity.md): Evidence severity accepted by diagnostic delivery.
- [Enum Diagnostic Read Reason](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/enum-diagnosticreadreason.md): Canonical diagnostic read reason values from the shared runtime types.
- [Enum Diagnostic Receipt Status](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/enum-diagnosticreceiptstatus.md): Terminal admission outcome for an ordered diagnostic submission.
- [Enum Diagnostic Summary Scope](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/enum-diagnosticsummaryscope.md): Aggregation scope of the reported lifetime summaries.
- [Enum Duration Unit](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/enum-durationunit.md): Canonical duration unit values from the shared runtime types.
- [Enum LlmOptimization Evidence Quality](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/enum-llmoptimizationevidencequality.md): Whether token evidence was observed or estimated.
- [Enum LlmOptimization Summary Status](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/enum-llmoptimizationsummarystatus.md): Whether optimization accounting is complete or limited by missing evidence.
- [Enum LogSeverity](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/enum-logseverity.md): Log evidence severity; an unspecified submitted severity is invalid.
- [Enum Memory Field Scope](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/enum-memoryfieldscope.md): Canonical memory field scope values from the shared runtime types.
- [Enum Plugin Diagnostic Family](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/enum-plugindiagnosticfamily.md): Canonical plugin diagnostic family values from the shared runtime types.
- [Enum Registration Surface](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/enum-registrationsurface.md): Closed registration surfaces; unspecified and unknown values cannot be invoked.
- [Enum Resource Association](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/enum-resourceassociation.md): Canonical resource association values from the shared runtime types.
- [Enum Resource Limit Event Kind](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/enum-resourcelimiteventkind.md): Canonical resource limit event kind values from the shared runtime types.
- [Enum Resource Limit Resource](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/enum-resourcelimitresource.md): Canonical resource limit resource values from the shared runtime types.
- [Enum Resource Measurement Scope](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/enum-resourcemeasurementscope.md): Canonical resource measurement scope values from the shared runtime types.
- [Enum Resource Memory Availability](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/enum-resourcememoryavailability.md): Canonical resource memory availability values from the shared runtime types.
- [Enum Resource Operating System](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/enum-resourceoperatingsystem.md): Canonical resource operating system values from the shared runtime types.
- [Enum Resource Sample Stream](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/enum-resourcesamplestream.md): Canonical resource sample stream values from the shared runtime types.
- [Enum Scope Category](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/enum-scopecategory.md): Scope lifecycle phase; unspecified is invalid for emitted scope events.
- [Enum Scope Type](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/enum-scopetype.md): Recognized runtime scope types, including the explicit unknown-category fallback.
- [Enum Worker Health Status](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/enum-workerhealthstatus.md): Worker readiness state; unspecified is not a readiness assertion.
- [Constant CONTRACT_VERSION](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/constant-contract-version.md): Initial stable worker/schema contract baseline, independent of crate versions.
- [Constant DIAGNOSTIC_PROVENANCE_CONTRACT_VERSION](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/constant-diagnostic-provenance-contract-version.md): Diagnostic provenance contract negotiated independently of the worker protocol.
- [Constant DIAGNOSTIC_SNAPSHOT_CONTRACT_VERSION](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/constant-diagnostic-snapshot-contract-version.md): Diagnostic snapshot contract negotiated independently of the worker protocol.
- [Constant WORKER_PROTOCOL](https://docs.nvidia.com/nemo/relay/dev/reference/api/rust-library-reference/nemo-relay-worker-proto/nvidia_worker_v1/constant-worker-protocol.md): Negotiation identifier for this contract, incompatible with legacy grpc-v1.