Description

The 60s timeout, how can we increase that? This is very problematic as local compute can be slow and the work will fail because it timeout too early!

[4/8] Setting up inference provider
  ──────────────────────────────────────────────────
✓ Active gateway set to 'nemoclaw'
✓ Created provider ollama-local
Gateway inference configured:

  Route: inference.local
  Provider: ollama-local
  Model: qwen3.5:35b
  Version: 1
  Timeout: 60s (default)
  Priming Ollama model: qwen3.5:35b
  ✓ Inference route set: ollama-local / qwen3.5:35b

Reproduction Steps

nemoclaw onboard

then no option to change the timeout

Environment

Spark

Debug Output

Logs

Checklist

• I confirmed this bug is reproducible
• I searched existing issues and this is not a duplicate