For AI agents: a documentation index is available at the root level at /llms.txt and /llms-full.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
  • About NVIDIA NeMo Relay
    • Overview
    • Architecture
    • Ecosystem
    • Concepts
    • Release Notes
  • Getting Started
    • Agent Runtime Primer
    • Prerequisites
    • Installation
    • Configuration / Setup
    • Quick Start
  • NVIDIA NeMo Relay CLI
    • About
    • Basic Usage
    • Claude Code
    • Codex
    • Cursor
    • Hermes Agent
  • Supported Integrations
    • About
    • OpenClaw Plugin Guide
    • LangChain Integration Guide
    • LangGraph Integration Guide
    • Deep Agents Integration Guide
  • Instrument Applications
    • About
    • Adding Scopes and Marks
    • Instrument a Tool Call
    • Instrument an LLM Call
    • Add Middleware
    • Code Examples
  • Observability Plugin
    • About
    • Configuration
    • Agent Trajectory Interchange Format (ATIF)
    • Agent Trajectory Observability Format (ATOF)
    • OpenTelemetry
    • OpenInference
  • Adaptive Plugin
    • About
    • Configuration
    • Adaptive Cache Governor (ACG)
    • Adaptive Hints
  • NeMo Guardrails Plugin
    • About
    • Configuration
  • Integrate into Frameworks
    • About
    • Adding Scopes
    • Wrap Tool Calls
    • Wrap LLM Calls
    • Handle Non-Serializable Data
    • Using Codecs
    • Provider Codecs
    • Provider Response Codecs
    • Code Examples
  • Build Plugins
    • About
    • Define a Plugin
    • Validate Plugin Configuration
    • Plugin Configuration Files
    • Register Plugin Behavior
    • Design Plugin Configuration
    • NeMo Guardrails Example Plugin
    • Code Examples
  • Contribute
    • About
    • Development Setup
    • Workflow and Reviews
    • Testing and Documentation
  • Reference
    • APIs
      • Python Library Reference
      • Node.js Library Reference
      • Rust Library Reference
        • nemo-relay
        • nemo-relay-adaptive
          • acg
            • anthropic_plugin
            • canonicalize
            • capability
            • ir_builder
            • openai_plugin
            • passthrough
            • plugin
            • plugin_registry
            • policy
            • profile
            • prompt_ir
              • PromptBlock
              • PromptIR
              • SpanId
              • TokenizationMetadata
              • ToolSchemaHash
              • BlockContentType
              • PromptRole
              • ProvenanceLabel
              • SensitivityLabel
            • retention
            • stability
            • telemetry
            • types
            • variable_extractor
            • error
            • MIN_ACG_OBSERVATIONS
          • acg_component
          • acg_learner
          • acg_profile
          • adaptive_hints_intercept
          • cache_diagnostics
          • config
          • context_helpers
          • drain
          • error
          • intercepts
          • learner
          • plugin_component
          • redis
          • storage
          • subscriber
          • tool_parallelism_learner
          • trie
          • types
          • AdaptiveRuntime
        • nemo-relay-ffi
    • Performance
  • Resources
    • Support and FAQs
    • Glossary
    • Troubleshooting Guide
    • Community
    • Legal
NVIDIANVIDIA
Developer-friendly docs for your API
Privacy Policy | Your Privacy Choices | Terms of Service | Accessibility | Corporate Policies | Product Security | Contact

Copyright © 2026, NVIDIA Corporation.

LogoLogo
On this page
  • Structs
  • Enums
ReferenceAPIsRust Library Referencenemo-relay-adaptiveacg

Module prompt_ir

||View as Markdown|
Previous

Enum Stability Class

Next

Struct Prompt Block

Generated from cargo doc --no-deps -p nemo-relay -p nemo-relay-adaptive -p nemo-relay-ffi.

Prompt Intermediate Representation (IR) types for the Adaptive Cache Governor (ACG) system.

The Prompt IR decomposes LLM conversations into addressable blocks with structural metadata for cache analysis and prompt rewriting. This is deliberately different from the message-oriented AnnotatedLlmRequest in core - the IR flattens the hierarchy into a sequence of blocks, each carrying provenance, sensitivity, and stability metadata.

Structs

  • PromptBlock: A single addressable block within the Prompt IR.
  • PromptIR: Prompt Intermediate Representation - the full decomposed prompt.
  • SpanId: Stable span identifier for addressable prompt blocks.
  • TokenizationMetadata: Token count metadata for a prompt block.
  • ToolSchemaHash: Hash fingerprint of a tool schema definition.

Enums

  • BlockContentType: Content type discriminant for a prompt block.
  • PromptRole: Role of a prompt block within the conversation.
  • ProvenanceLabel: Origin label for a prompt block.
  • SensitivityLabel: Sensitivity classification for a prompt block.