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

# Module adaptive_hints_intercept

> AdaptiveHintsIntercept: opt-in LLM request intercept that injects AgentHints from HotCache trie.

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

AdaptiveHintsIntercept: opt-in LLM request intercept that injects AgentHints from HotCache trie.

This module provides [`AdaptiveHintsIntercept`](/reference/api/rust-library-reference/nemo-relay-adaptive/adaptive_hints_intercept/struct-adaptivehintsintercept), which builds [`AgentHints`](/reference/api/rust-library-reference/nemo-relay-adaptive/types/metadata/struct-agenthints) from the prediction trie in [`HotCache`](/reference/api/rust-library-reference/nemo-relay-adaptive/types/cache/struct-hotcache) and injects them into LLM request headers as a request intercept. AdaptiveHintsIntercept is opt-in and synchronously transforms the [`LlmRequest`](/reference/api/rust-library-reference/nemo-relay/api/llm/struct-llmrequest) before it reaches the callable.

## Structs

* [AdaptiveHintsIntercept](/reference/api/rust-library-reference/nemo-relay-adaptive/adaptive_hints_intercept/struct-adaptivehintsintercept): Opt-in LLM request intercept that injects [`AgentHints`](/reference/api/rust-library-reference/nemo-relay-adaptive/types/metadata/struct-agenthints) into request headers from the prediction trie in [`HotCache`](/reference/api/rust-library-reference/nemo-relay-adaptive/types/cache/struct-hotcache).