fix(plugin): show actual configured model in banner (Closes #24)

[WuKongAI-CMU]

Summary

When the onboard config file is not available (e.g. when running inside the sandbox), the plugin banner in `nemoclaw/src/index.ts` hardcodes the model as `nvidia/nemotron-3-super-120b-a12b` and the endpoint as `build.nvidia.com` regardless of what is actually configured in OpenShell.

This PR queries the live OpenShell inference state via `openshell inference get --json` as a fallback before resorting to hardcoded defaults. The probe has a 3-second timeout and falls back cleanly to the existing defaults if anything goes wrong.

Closes #24.

Changes

• `nemoclaw/src/index.ts` — add `probeOpenShellInference()` helper and wire it into banner resolution after onboard config lookup, before hardcoded defaults

Test plan

• Minimal diff, existing defaults preserved as final fallback
• 3s timeout prevents banner from hanging on a slow/broken openshell binary
• No new runtime dependencies (uses stdlib `node:child_process`)

🤖 Generated with Claude Code

Summary by CodeRabbit

• New Features
  • Added automatic detection of inference configuration from OpenShell. The system now prioritizes onboard configuration settings, attempts auto-detection from OpenShell, and uses default values as a final fallback.

[github-actions]

This repository limits contributors to 10 open pull requests. Please close or merge existing PRs before opening new ones.

[coderabbitai]

Caution

Review failed

The pull request is closed.

ℹ️ Recent review info

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Pro

Run ID: 2f3c8145-600b-4391-ba43-c75adb6ad7ca

📥 Commits

Reviewing files that changed from the base of the PR and between d4aac4c and dbd9b9f.

📒 Files selected for processing (1)

• nemoclaw/src/index.ts

---

📝 Walkthrough

Walkthrough

Added a probeOpenShellInference() helper function that executes openshell inference get --json to detect the actual configured inference provider and model. Updated register() to prioritize onboard configuration, fall back to probed values, and only use hardcoded defaults as a last resort.

Changes

Cohort / File(s)	Summary
Dynamic Inference Provider Detection nemoclaw/src/index.ts	Introduced probeOpenShellInference() helper that invokes openshell inference get --json via execFileSync, parses the JSON output, and returns endpoint and model values. Modified register() initialization logic to follow a fallback chain: prefer config-derived values, probe openshell if needed, and use hardcoded defaults only as a final fallback. Added node:child_process import.

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~10 minutes

Poem

🐰 A rabbit hops through code so bright,
No more defaults baked too tight!
We probe the shell, detect what's real,
The truthful model we now reveal! 🔍

✨ Finishing Touches

🧪 Generate unit tests (beta)

• Create PR with unit tests

---

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