feat: add skill-load coverage for agent integrations [2/3]

[willkill07]

Overview

Extends RELAY-443 coverage into the supported agent integrations. This is the second commit in a three-PR cumulative stack; all three PRs target upstream main as requested, so this PR temporarily includes the first commit until it merges.

• 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 skill-load hook coverage for the Claude Code and Codex coding-agent integrations.
• Adds real LangChain, LangGraph, and Deep Agents coverage while preserving the existing Deep Agents configured-skills mark.
• Keeps all test bodies outside implementation src trees.
• Removes all OpenClaw changes; that integration work will be refactored separately.

Validation: just test-rust, just test-python, just test-node, and uv run pre-commit run --all-files.

Breaking changes: none.

Where should the reviewer start?

Start with crates/core/src/api/skill_load.rs, then review the coding-agent hook configurations and Python integration coverage.

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

• Relates to: RELAY-443

[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: 24c1677d-74d7-4586-8e9a-85994dc34620

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

✨ Finishing Touches

🧪 Generate unit tests (beta)

• Create PR with unit tests

---

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

[github-actions]

Fern docs preview: https://nvidia-preview-pull-request-392.docs.buildwithfern.com/nemo/relay (​https://nvidia-preview-pull-request-392.docs.buildwithfern.com/nemo/relay​)

[github-actions]

License Diff

Compared against origin/main.

Lockfile license changes

Lockfile License Changes

Rust

Added

• None

Removed

• None

Updated/Changed

• None

Node

Added

• None

Removed

• None

Updated/Changed

• None

Python

Added

• None

Removed

• None

Updated/Changed

• None

Status output

[license-diff] selected languages: rust, node, python
[license-diff] generating current inventory
[license-diff] current: generating Rust inventory
[license-diff] current: Rust inventory complete (378 packages)
[license-diff] current: generating Node inventory
[license-diff] current: Node inventory complete (363 packages)
[license-diff] current: generating Python inventory
[license-diff] current: Python inventory complete (105 packages)
[license-diff] current inventory complete
[license-diff] checking out base ref origin/main into a temporary worktree
[license-diff] base: generating Rust inventory
[license-diff] base: Rust inventory complete (378 packages)
[license-diff] base: generating Node inventory
[license-diff] base: Node inventory complete (363 packages)
[license-diff] base: generating Python inventory
[license-diff] base: Python inventory complete (105 packages)
[license-diff] base inventory complete
[license-diff] removing temporary base worktree
[license-diff] comparing inventories
[license-diff] rendering Markdown output
[license-diff] done

[mnajafian-nv]

I’d drop the OpenClaw-specific skill-load handling from this stack. With the CLI/sidecar pivot, extending hook replay with eager/fallback state looks like unnecessary complexity. I’d keep the shared core and other integration changes, remove the corresponding OpenClaw changes from 392/393, and handle managed OpenClaw skill marks at the sidecar boundary if we still need them. That would also make my OpenClaw-specific inline comments moot.