docs(adaptive): document opt-in tool result caching

[zhongxuanwang-nv]

Overview

Documents the opt-in Adaptive tool-result cache introduced in #597, including its safety constraints and configuration.

• I confirm this contribution is my own work, or I have the right to submit it under this project's license.
• I searched existing issues and open pull requests, and this does not duplicate existing work.

Details

• Adds tool-cache configuration and safe usage guidance: only explicitly classified read-only, TTL-stable tools are eligible.
• Documents class and per-tool policy resolution, cache-key versioning, observability marks, nemo-relay doctor output, and validation diagnostics.
• Clarifies the shared cache observability fields for LLM token savings versus tool invocation savings.
• Breaking changes: none.
• Validation: just docs, just docs-linkcheck, and uv run pre-commit run --files docs/configure-plugins/adaptive/response-cache.mdx.

Where should the reviewer start?

Start with the Tool-Result Cache section in docs/configure-plugins/adaptive/response-cache.mdx.

Related Issues: (use one of the action keywords Closes / Fixes / Resolves / Relates to)

• Relates to #597

[coderabbitai]

Important

Review skipped

Draft detected.

Please check the settings in the CodeRabbit UI or the .coderabbit.yaml file in this repository. To trigger a single review, invoke the @coderabbitai review command.

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: ASSERTIVE

Plan: Enterprise

Run ID: a0455eb6-eae1-48ca-b95d-eeecd0bd07bc

You can disable this status message by setting the reviews.review_status to false in the CodeRabbit configuration file.

Use the checkbox below for a quick retry:

• 🔍 Trigger review

---

_{Comment @coderabbitai help to get the list of available commands.}

[github-actions]

Fern docs preview: https://nvidia-preview-pull-request-598.docs.buildwithfern.com/nemo/relay/dev