RLM Debug — Runtime Diagnostics

Use this skill when the question is not "how do I use fleet-rlm?" but "why is fleet-rlm not behaving correctly?"

Runtime: daytona_pilot

daytona_pilot is the primary runtime. Daytona is the interpreter/sandbox backend.

Canonical Checks

# from repo root
uv run fleet web
uv run fleet-rlm serve-api --port 8000
uv run fleet-rlm daytona-smoke --repo <url> [--ref <branch>]
make test-fast