// Use when debugging a Nemo Gym run or reward profiling job. Covers rollout collection failures, empty or partial JSONL outputs, stale materialized inputs, verifier/schema errors, Ray or Slurm issues, vLLM readiness, judge failures, tool/sandbox failures, cache problems, and throughput bottlenecks.
| name | nemo-gym-debugging |
| description | Use when debugging a Nemo Gym run or reward profiling job. Covers rollout collection failures, empty or partial JSONL outputs, stale materialized inputs, verifier/schema errors, Ray or Slurm issues, vLLM readiness, judge failures, tool/sandbox failures, cache problems, and throughput bottlenecks. |
Use this skill when something failed or looks suspicious in a Nemo Gym run. If the task is adding a new env, use $nemo-gym-env-integration; if it is changing profiling behavior, use $nemo-gym-reward-profiling.
Debug by classification, not by guessing. The first goal is to decide whether the issue is:
/models availability.resume_from_cache was enabled, stale materialized inputs are a first-class suspect.references/vllm-tool-call-schema-checks.md and run a static tool-schema check before changing Gym wrappers.++global_aiohttp_client_request_debug=True. Read references/request-boundary-visibility.md before changing code.references/error-profiles.md to classify the failing layer before changing code or data.references/diagnostic-snippets.md when you need copy-paste commands to inspect logs, output counts, materialized inputs, rollout JSONL shape, server readiness, or reward summaries without mutating run state.references/vllm-tool-call-schema-checks.md when a tool-call dataset may be rejected by vLLM/Outlines grammar compilation before any meaningful generation happens.references/request-boundary-visibility.md when /run 500s hide row identity or nested Gym 500s hide the inner model/verifier/provider error. It covers the existing Gym debug flag, shipped request-boundary markers, empty provider bodies, and vLLM provider-side escalation.When reporting back, state:
Use when debugging a Nemo Gym run or reward profiling job. Covers rollout collection failures, empty or partial JSONL outputs, stale materialized inputs, verifier/schema errors, Ray or Slurm issues, vLLM readiness, judge failures, tool/sandbox failures, cache problems, and throughput bottlenecks.
Use when creating, validating, or documenting Nemo Gym pivot datasets from rollout, trajectory, chat-completion, Responses API, or tool-call artifacts. Covers Gym Responses-style row conversion, pivot selection, single-step tool-use configs, agent_ref alignment, verifier knobs, expected-action row contracts, and train/eval usage.
Use to help users get started with Nemo Gym reward profiling. Covers the basic ng_run, ng_collect_rollouts, and ng_reward_profile workflow, repeated rollouts, materialized inputs, rollout JSONL artifacts, task and rollout identity, output inspection, partial profiling, and rollout_infos. For failed jobs, prefer nemo-gym-debugging.
Use when creating, validating, or documenting Nemo Gym pivot datasets from rollout, trajectory, chat-completion, Responses API, or tool-call artifacts. Covers Gym Responses-style row conversion, pivot selection, single-step tool-use configs, agent_ref alignment, verifier knobs, expected-action row contracts, and train/eval usage.
Use to help users get started with Nemo Gym reward profiling. Covers the basic ng_run, ng_collect_rollouts, and ng_reward_profile workflow, repeated rollouts, materialized inputs, rollout JSONL artifacts, task and rollout identity, output inspection, partial profiling, and rollout_infos. For failed jobs, prefer nemo-gym-debugging.
Maintain the NeMo Gym Fern docs site — add, update, move, or remove pages under fern/. Use for any documentation change. Triggered by: "edit docs", "add doc page", "update docs", "rename page", "fix broken link", "add redirect", "preview docs", "publish docs", any request that touches `fern/`.