[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-nvidia-i4h-workflow-dataset-replay":3,"mdc--cyr6jw-key":31,"related-org-nvidia-i4h-workflow-dataset-replay":1627,"related-repo-nvidia-i4h-workflow-dataset-replay":1788},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":11,"stars":20,"repoUrl":21,"updatedAt":22,"license":23,"forks":24,"topics":25,"repo":26,"sourceUrl":29,"mdContent":30},"i4h-workflow-dataset-replay","replay HDF5 recordings in Isaac Sim","Replay a recorded HDF5 episode inside Isaac Sim for visual verification. Use when the user asks to replay, play back, or step through an HDF5 recording.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},"nvidia","NVIDIA","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fnvidia.png",[12,16,17],{"name":13,"slug":14,"type":15},"Robotics","robotics","tag",{"name":9,"slug":8,"type":15},{"name":18,"slug":19,"type":15},"Simulation","simulation",2473,"https:\u002F\u002Fgithub.com\u002FNVIDIA\u002Fskills","2026-07-23T06:06:04.324182","Apache-2.0",281,[],{"repoUrl":21,"stars":20,"forks":24,"topics":27,"description":28},[],"AI agent skills published by NVIDIA","https:\u002F\u002Fgithub.com\u002FNVIDIA\u002Fskills\u002Ftree\u002FHEAD\u002Fskills\u002Fi4h-workflow-dataset-replay","---\nname: i4h-workflow-dataset-replay\nversion: \"0.6.0\"\ndescription: Replay a recorded HDF5 episode inside Isaac Sim for visual verification. Use when the user asks to replay, play back, or step through an HDF5 recording.\nlicense: Apache-2.0\nmetadata:\n  author: \"Isaac for Healthcare Team \u003Cisaac-for-healthcare-support@nvidia.com>\"\n  tags:\n    - isaac-for-healthcare\n    - i4h\n    - dataset\n    - replay\n    - hdf5\n---\n\n# i4h Workflow — Replay Dataset\n\n## Purpose\n\nReplay a recorded HDF5 episode inside Isaac Sim for visual verification. Use when the user asks to replay, play back, or step through an HDF5 recording.\n\n## Base Code\n\nThese steps drive the i4h-workflows base code (the `workflows\u002Fagentic\u002F` tree). To reuse an existing checkout, set `I4H_WORKFLOWS` to its path (no clone happens). Otherwise this resolves the current repo, or clones to `~\u002Fi4h-workflows` — pick that default without prompting. Run every command below from the resolved root:\n\n```bash\n# Resolve the i4h-workflows base code (provides workflows\u002Fagentic\u002F).\nROOT=\"${I4H_WORKFLOWS:-$(git rev-parse --show-toplevel 2>\u002Fdev\u002Fnull)}\"\nif [ ! -d \"$ROOT\u002Fworkflows\u002Fagentic\" ]; then\n  ROOT=\"${I4H_WORKFLOWS:-$HOME\u002Fi4h-workflows}\"\n  [ -d \"$ROOT\u002Fworkflows\u002Fagentic\" ] || git clone https:\u002F\u002Fgithub.com\u002Fisaac-for-healthcare\u002Fi4h-workflows \"$ROOT\"\nfi\nexport I4H_WORKFLOWS=\"$ROOT\"; cd \"$ROOT\"\n```\n\n## Basics\n\n- **Env config (source of truth):** `workflows\u002Fagentic\u002Fconfig\u002Fenvironments\u002F\u003Cenv>.yaml` — the `\u003Cenv>` scene, robot, and cameras Arena replays against.\n- Replay runs `arena\u002Frun.sh --replay` against the env that produced the HDF5.\n- Use it to verify visual correctness before conversion or training.\n- Interpret ordinal wording as zero-based episode indices: \"first episode\" -> `0`, \"second episode\" -> `1`, etc.\n\n## Run\n\nRun the steps below in order. Each step is a separate bash call; variables persist in the local agent's tmux session.\n\n### Step 1 — setup and resolve HDF5\n\n```bash\nREPO_ROOT=\"${I4H_WORKFLOWS:-$(git rev-parse --show-toplevel 2>\u002Fdev\u002Fnull)}\"; [ -d \"$REPO_ROOT\u002Fworkflows\u002Fagentic\" ] || REPO_ROOT=\"$HOME\u002Fi4h-workflows\"\nENV_ID=scissor_pick_and_place\nRUNS_ROOT=\"${REPO_ROOT}\u002Fworkflows\u002Fagentic\u002Fruns\"\nEPISODE_INDEX=\"${EPISODE_INDEX:-0}\"  # For \"Replay second episode\", set EPISODE_INDEX=1.\n\n# Point HDF5_PATH at a real recording (absolute path). Recordings come from teleop, mimic, or\n# validate (which writes data\u002Fverify.hdf5 under each runs\u002Feval_* dir). List candidates newest-first:\n#   find \"${RUNS_ROOT}\" -name '*.hdf5' -printf '%TY-%Tm-%Td %TH:%TM  %p\\n' | sort -r | head\nHDF5_PATH=\"${HDF5_PATH:-}\"\nif [ ! -f \"${HDF5_PATH}\" ]; then\n  echo \"replay: set HDF5_PATH to an existing .hdf5 (got '${HDF5_PATH:-\u003Cunset>}'). Candidates:\" >&2\n  find \"${RUNS_ROOT}\" -name '*.hdf5' -printf '%TY-%Tm-%Td %TH:%TM  %p\\n' 2>\u002Fdev\u002Fnull | sort -r | head\n  exit 1\nfi\n\nRUN_DIR=\"${RUNS_ROOT}\u002Freplay_${ENV_ID}_$(date +%Y%m%d_%H%M%S)\"\nmkdir -p \"${RUN_DIR}\u002Flogs\"\nln -sfn \"${RUN_DIR}\" \"${RUNS_ROOT}\u002F.latest\"\n```\n\n### Step 2 — replay\n\n```bash\n\"${REPO_ROOT}\u002Fworkflows\u002Fagentic\u002Farena\u002Frun.sh\" \\\n  --env \"${ENV_ID}\" \\\n  --replay \"${HDF5_PATH}\" \\\n  --episode-index \"${EPISODE_INDEX}\" \\\n  2>&1 | tee \"${RUN_DIR}\u002Flogs\u002Freplay.log\"\n```\n\n## Notes\n\n- `HDF5_PATH` must be an absolute path to an existing recording — `--replay` resolves a relative path against `runs\u002F\u003Cenv>\u002F`, not your cwd, so a bare\u002Frelative path silently fails to load. The block lists real candidates if it's unset or wrong.\n- Recordings come from [[i4h-workflow-dataset-teleop]], [[i4h-workflow-dataset-mimic]], or [[i4h-workflow-validate]] (validate writes `data\u002Fverify.hdf5` under each `runs\u002Feval_*` dir). There is no default `demo.hdf5`.\n- `--episode-index` selects the episode within the HDF5 (zero-based).\n- For \"Replay second episode\", use `--episode-index 1`.\n- Use the same env id as the env that produced the recording.\n\n## Prerequisites\n\n- Workflow set up via [[i4h-workflow-setup]] (the `.venv` must exist).\n- An existing HDF5 recording to replay.\n- The env id that produced the recording.\n\n## Limitations\n\n- Visual verification only; replay does not modify or expand the recording.\n- Replays one episode per invocation, selected by `--episode-index`.\n- Runs inside Isaac Sim; the env id must match the one that produced the HDF5.\n\n## Troubleshooting\n\n- **Error:** `.venv` not found \u002F replay fails to launch - Cause: workflow not set up. Fix: run [[i4h-workflow-setup]] first.\n- **Error:** `replay: set HDF5_PATH to an existing .hdf5` (or recording fails to load) - Cause: `HDF5_PATH` unset or not a real file. Fix: pick an absolute path from the printed candidates (e.g. a `verify.hdf5` under `runs\u002Feval_*\u002Fdata\u002F`).\n- **Error:** episode index out of range - Cause: `--episode-index` exceeds the episodes in the HDF5. Fix: use a valid zero-based index.\n- **Error:** mismatched\u002Fgarbled playback - Cause: `--env` differs from the env that produced the recording. Fix: use the same env id.\n\n## Final Response\n\nReport env, HDF5 path, episode index, launch outcome, visible mismatches.\n",{"data":32,"body":42},{"name":4,"version":33,"description":6,"license":23,"metadata":34},"0.6.0",{"author":35,"tags":36},"Isaac for Healthcare Team \u003Cisaac-for-healthcare-support@nvidia.com>",[37,38,39,40,41],"isaac-for-healthcare","i4h","dataset","replay","hdf5",{"type":43,"children":44},"root",[45,54,61,66,72,102,444,450,521,527,532,539,1207,1213,1359,1365,1451,1457,1483,1489,1513,1519,1610,1616,1621],{"type":46,"tag":47,"props":48,"children":50},"element","h1",{"id":49},"i4h-workflow-replay-dataset",[51],{"type":52,"value":53},"text","i4h Workflow — Replay Dataset",{"type":46,"tag":55,"props":56,"children":58},"h2",{"id":57},"purpose",[59],{"type":52,"value":60},"Purpose",{"type":46,"tag":62,"props":63,"children":64},"p",{},[65],{"type":52,"value":6},{"type":46,"tag":55,"props":67,"children":69},{"id":68},"base-code",[70],{"type":52,"value":71},"Base Code",{"type":46,"tag":62,"props":73,"children":74},{},[75,77,84,86,92,94,100],{"type":52,"value":76},"These steps drive the i4h-workflows base code (the ",{"type":46,"tag":78,"props":79,"children":81},"code",{"className":80},[],[82],{"type":52,"value":83},"workflows\u002Fagentic\u002F",{"type":52,"value":85}," tree). To reuse an existing checkout, set ",{"type":46,"tag":78,"props":87,"children":89},{"className":88},[],[90],{"type":52,"value":91},"I4H_WORKFLOWS",{"type":52,"value":93}," to its path (no clone happens). Otherwise this resolves the current repo, or clones to ",{"type":46,"tag":78,"props":95,"children":97},{"className":96},[],[98],{"type":52,"value":99},"~\u002Fi4h-workflows",{"type":52,"value":101}," — pick that default without prompting. Run every command below from the resolved root:",{"type":46,"tag":103,"props":104,"children":109},"pre",{"className":105,"code":106,"language":107,"meta":108,"style":108},"language-bash shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","# Resolve the i4h-workflows base code (provides workflows\u002Fagentic\u002F).\nROOT=\"${I4H_WORKFLOWS:-$(git rev-parse --show-toplevel 2>\u002Fdev\u002Fnull)}\"\nif [ ! -d \"$ROOT\u002Fworkflows\u002Fagentic\" ]; then\n  ROOT=\"${I4H_WORKFLOWS:-$HOME\u002Fi4h-workflows}\"\n  [ -d \"$ROOT\u002Fworkflows\u002Fagentic\" ] || git clone https:\u002F\u002Fgithub.com\u002Fisaac-for-healthcare\u002Fi4h-workflows \"$ROOT\"\nfi\nexport I4H_WORKFLOWS=\"$ROOT\"; cd \"$ROOT\"\n","bash","",[110],{"type":46,"tag":78,"props":111,"children":112},{"__ignoreMap":108},[113,125,215,270,313,381,390],{"type":46,"tag":114,"props":115,"children":118},"span",{"class":116,"line":117},"line",1,[119],{"type":46,"tag":114,"props":120,"children":122},{"style":121},"--shiki-light:#90A4AE;--shiki-light-font-style:italic;--shiki-default:#546E7A;--shiki-default-font-style:italic;--shiki-dark:#676E95;--shiki-dark-font-style:italic",[123],{"type":52,"value":124},"# Resolve the i4h-workflows base code (provides workflows\u002Fagentic\u002F).\n",{"type":46,"tag":114,"props":126,"children":128},{"class":116,"line":127},2,[129,135,141,146,150,155,161,166,171,176,181,186,191,196,200,205,210],{"type":46,"tag":114,"props":130,"children":132},{"style":131},"--shiki-light:#90A4AE;--shiki-default:#EEFFFF;--shiki-dark:#BABED8",[133],{"type":52,"value":134},"ROOT",{"type":46,"tag":114,"props":136,"children":138},{"style":137},"--shiki-light:#39ADB5;--shiki-default:#89DDFF;--shiki-dark:#89DDFF",[139],{"type":52,"value":140},"=",{"type":46,"tag":114,"props":142,"children":143},{"style":137},[144],{"type":52,"value":145},"\"${",{"type":46,"tag":114,"props":147,"children":148},{"style":131},[149],{"type":52,"value":91},{"type":46,"tag":114,"props":151,"children":152},{"style":137},[153],{"type":52,"value":154},":-",{"type":46,"tag":114,"props":156,"children":158},{"style":157},"--shiki-light:#91B859;--shiki-default:#C3E88D;--shiki-dark:#C3E88D",[159],{"type":52,"value":160},"$(",{"type":46,"tag":114,"props":162,"children":163},{"style":131},[164],{"type":52,"value":165},"git",{"type":46,"tag":114,"props":167,"children":168},{"style":131},[169],{"type":52,"value":170}," rev-parse",{"type":46,"tag":114,"props":172,"children":173},{"style":131},[174],{"type":52,"value":175}," --show-toplevel",{"type":46,"tag":114,"props":177,"children":178},{"style":131},[179],{"type":52,"value":180}," 2",{"type":46,"tag":114,"props":182,"children":183},{"style":157},[184],{"type":52,"value":185},">",{"type":46,"tag":114,"props":187,"children":188},{"style":137},[189],{"type":52,"value":190},"\u002F",{"type":46,"tag":114,"props":192,"children":193},{"style":131},[194],{"type":52,"value":195},"dev",{"type":46,"tag":114,"props":197,"children":198},{"style":137},[199],{"type":52,"value":190},{"type":46,"tag":114,"props":201,"children":202},{"style":131},[203],{"type":52,"value":204},"null",{"type":46,"tag":114,"props":206,"children":207},{"style":157},[208],{"type":52,"value":209},")",{"type":46,"tag":114,"props":211,"children":212},{"style":137},[213],{"type":52,"value":214},"}\"\n",{"type":46,"tag":114,"props":216,"children":218},{"class":116,"line":217},3,[219,225,230,235,240,245,250,255,260,265],{"type":46,"tag":114,"props":220,"children":222},{"style":221},"--shiki-light:#39ADB5;--shiki-light-font-style:italic;--shiki-default:#89DDFF;--shiki-default-font-style:italic;--shiki-dark:#89DDFF;--shiki-dark-font-style:italic",[223],{"type":52,"value":224},"if",{"type":46,"tag":114,"props":226,"children":227},{"style":137},[228],{"type":52,"value":229}," [",{"type":46,"tag":114,"props":231,"children":232},{"style":137},[233],{"type":52,"value":234}," !",{"type":46,"tag":114,"props":236,"children":237},{"style":137},[238],{"type":52,"value":239}," -d",{"type":46,"tag":114,"props":241,"children":242},{"style":137},[243],{"type":52,"value":244}," \"",{"type":46,"tag":114,"props":246,"children":247},{"style":131},[248],{"type":52,"value":249},"$ROOT",{"type":46,"tag":114,"props":251,"children":252},{"style":157},[253],{"type":52,"value":254},"\u002Fworkflows\u002Fagentic",{"type":46,"tag":114,"props":256,"children":257},{"style":137},[258],{"type":52,"value":259},"\"",{"type":46,"tag":114,"props":261,"children":262},{"style":137},[263],{"type":52,"value":264}," ];",{"type":46,"tag":114,"props":266,"children":267},{"style":221},[268],{"type":52,"value":269}," then\n",{"type":46,"tag":114,"props":271,"children":273},{"class":116,"line":272},4,[274,279,283,287,291,295,300,304,309],{"type":46,"tag":114,"props":275,"children":276},{"style":131},[277],{"type":52,"value":278},"  ROOT",{"type":46,"tag":114,"props":280,"children":281},{"style":137},[282],{"type":52,"value":140},{"type":46,"tag":114,"props":284,"children":285},{"style":137},[286],{"type":52,"value":145},{"type":46,"tag":114,"props":288,"children":289},{"style":131},[290],{"type":52,"value":91},{"type":46,"tag":114,"props":292,"children":293},{"style":137},[294],{"type":52,"value":154},{"type":46,"tag":114,"props":296,"children":297},{"style":131},[298],{"type":52,"value":299},"$HOME",{"type":46,"tag":114,"props":301,"children":302},{"style":137},[303],{"type":52,"value":190},{"type":46,"tag":114,"props":305,"children":306},{"style":131},[307],{"type":52,"value":308},"i4h-workflows",{"type":46,"tag":114,"props":310,"children":311},{"style":137},[312],{"type":52,"value":214},{"type":46,"tag":114,"props":314,"children":316},{"class":116,"line":315},5,[317,322,326,330,334,338,342,347,352,358,363,368,372,376],{"type":46,"tag":114,"props":318,"children":319},{"style":137},[320],{"type":52,"value":321},"  [",{"type":46,"tag":114,"props":323,"children":324},{"style":137},[325],{"type":52,"value":239},{"type":46,"tag":114,"props":327,"children":328},{"style":137},[329],{"type":52,"value":244},{"type":46,"tag":114,"props":331,"children":332},{"style":131},[333],{"type":52,"value":249},{"type":46,"tag":114,"props":335,"children":336},{"style":157},[337],{"type":52,"value":254},{"type":46,"tag":114,"props":339,"children":340},{"style":137},[341],{"type":52,"value":259},{"type":46,"tag":114,"props":343,"children":344},{"style":137},[345],{"type":52,"value":346}," ]",{"type":46,"tag":114,"props":348,"children":349},{"style":137},[350],{"type":52,"value":351}," ||",{"type":46,"tag":114,"props":353,"children":355},{"style":354},"--shiki-light:#E2931D;--shiki-default:#FFCB6B;--shiki-dark:#FFCB6B",[356],{"type":52,"value":357}," git",{"type":46,"tag":114,"props":359,"children":360},{"style":157},[361],{"type":52,"value":362}," clone",{"type":46,"tag":114,"props":364,"children":365},{"style":157},[366],{"type":52,"value":367}," https:\u002F\u002Fgithub.com\u002Fisaac-for-healthcare\u002Fi4h-workflows",{"type":46,"tag":114,"props":369,"children":370},{"style":137},[371],{"type":52,"value":244},{"type":46,"tag":114,"props":373,"children":374},{"style":131},[375],{"type":52,"value":249},{"type":46,"tag":114,"props":377,"children":378},{"style":137},[379],{"type":52,"value":380},"\"\n",{"type":46,"tag":114,"props":382,"children":384},{"class":116,"line":383},6,[385],{"type":46,"tag":114,"props":386,"children":387},{"style":221},[388],{"type":52,"value":389},"fi\n",{"type":46,"tag":114,"props":391,"children":393},{"class":116,"line":392},7,[394,400,405,409,413,417,421,426,432,436,440],{"type":46,"tag":114,"props":395,"children":397},{"style":396},"--shiki-light:#9C3EDA;--shiki-default:#C792EA;--shiki-dark:#C792EA",[398],{"type":52,"value":399},"export",{"type":46,"tag":114,"props":401,"children":402},{"style":131},[403],{"type":52,"value":404}," I4H_WORKFLOWS",{"type":46,"tag":114,"props":406,"children":407},{"style":137},[408],{"type":52,"value":140},{"type":46,"tag":114,"props":410,"children":411},{"style":137},[412],{"type":52,"value":259},{"type":46,"tag":114,"props":414,"children":415},{"style":131},[416],{"type":52,"value":249},{"type":46,"tag":114,"props":418,"children":419},{"style":137},[420],{"type":52,"value":259},{"type":46,"tag":114,"props":422,"children":423},{"style":137},[424],{"type":52,"value":425},";",{"type":46,"tag":114,"props":427,"children":429},{"style":428},"--shiki-light:#6182B8;--shiki-default:#82AAFF;--shiki-dark:#82AAFF",[430],{"type":52,"value":431}," cd",{"type":46,"tag":114,"props":433,"children":434},{"style":137},[435],{"type":52,"value":244},{"type":46,"tag":114,"props":437,"children":438},{"style":131},[439],{"type":52,"value":249},{"type":46,"tag":114,"props":441,"children":442},{"style":137},[443],{"type":52,"value":380},{"type":46,"tag":55,"props":445,"children":447},{"id":446},"basics",[448],{"type":52,"value":449},"Basics",{"type":46,"tag":451,"props":452,"children":453},"ul",{},[454,482,495,500],{"type":46,"tag":455,"props":456,"children":457},"li",{},[458,464,466,472,474,480],{"type":46,"tag":459,"props":460,"children":461},"strong",{},[462],{"type":52,"value":463},"Env config (source of truth):",{"type":52,"value":465}," ",{"type":46,"tag":78,"props":467,"children":469},{"className":468},[],[470],{"type":52,"value":471},"workflows\u002Fagentic\u002Fconfig\u002Fenvironments\u002F\u003Cenv>.yaml",{"type":52,"value":473}," — the ",{"type":46,"tag":78,"props":475,"children":477},{"className":476},[],[478],{"type":52,"value":479},"\u003Cenv>",{"type":52,"value":481}," scene, robot, and cameras Arena replays against.",{"type":46,"tag":455,"props":483,"children":484},{},[485,487,493],{"type":52,"value":486},"Replay runs ",{"type":46,"tag":78,"props":488,"children":490},{"className":489},[],[491],{"type":52,"value":492},"arena\u002Frun.sh --replay",{"type":52,"value":494}," against the env that produced the HDF5.",{"type":46,"tag":455,"props":496,"children":497},{},[498],{"type":52,"value":499},"Use it to verify visual correctness before conversion or training.",{"type":46,"tag":455,"props":501,"children":502},{},[503,505,511,513,519],{"type":52,"value":504},"Interpret ordinal wording as zero-based episode indices: \"first episode\" -> ",{"type":46,"tag":78,"props":506,"children":508},{"className":507},[],[509],{"type":52,"value":510},"0",{"type":52,"value":512},", \"second episode\" -> ",{"type":46,"tag":78,"props":514,"children":516},{"className":515},[],[517],{"type":52,"value":518},"1",{"type":52,"value":520},", etc.",{"type":46,"tag":55,"props":522,"children":524},{"id":523},"run",[525],{"type":52,"value":526},"Run",{"type":46,"tag":62,"props":528,"children":529},{},[530],{"type":52,"value":531},"Run the steps below in order. Each step is a separate bash call; variables persist in the local agent's tmux session.",{"type":46,"tag":533,"props":534,"children":536},"h3",{"id":535},"step-1-setup-and-resolve-hdf5",[537],{"type":52,"value":538},"Step 1 — setup and resolve HDF5",{"type":46,"tag":103,"props":540,"children":542},{"className":105,"code":541,"language":107,"meta":108,"style":108},"REPO_ROOT=\"${I4H_WORKFLOWS:-$(git rev-parse --show-toplevel 2>\u002Fdev\u002Fnull)}\"; [ -d \"$REPO_ROOT\u002Fworkflows\u002Fagentic\" ] || REPO_ROOT=\"$HOME\u002Fi4h-workflows\"\nENV_ID=scissor_pick_and_place\nRUNS_ROOT=\"${REPO_ROOT}\u002Fworkflows\u002Fagentic\u002Fruns\"\nEPISODE_INDEX=\"${EPISODE_INDEX:-0}\"  # For \"Replay second episode\", set EPISODE_INDEX=1.\n\n# Point HDF5_PATH at a real recording (absolute path). Recordings come from teleop, mimic, or\n# validate (which writes data\u002Fverify.hdf5 under each runs\u002Feval_* dir). List candidates newest-first:\n#   find \"${RUNS_ROOT}\" -name '*.hdf5' -printf '%TY-%Tm-%Td %TH:%TM  %p\\n' | sort -r | head\nHDF5_PATH=\"${HDF5_PATH:-}\"\nif [ ! -f \"${HDF5_PATH}\" ]; then\n  echo \"replay: set HDF5_PATH to an existing .hdf5 (got '${HDF5_PATH:-\u003Cunset>}'). Candidates:\" >&2\n  find \"${RUNS_ROOT}\" -name '*.hdf5' -printf '%TY-%Tm-%Td %TH:%TM  %p\\n' 2>\u002Fdev\u002Fnull | sort -r | head\n  exit 1\nfi\n\nRUN_DIR=\"${RUNS_ROOT}\u002Freplay_${ENV_ID}_$(date +%Y%m%d_%H%M%S)\"\nmkdir -p \"${RUN_DIR}\u002Flogs\"\nln -sfn \"${RUN_DIR}\" \"${RUNS_ROOT}\u002F.latest\"\n",[543],{"type":46,"tag":78,"props":544,"children":545},{"__ignoreMap":108},[546,682,699,733,770,779,787,795,804,830,872,935,1028,1043,1051,1059,1125,1160],{"type":46,"tag":114,"props":547,"children":548},{"class":116,"line":117},[549,554,558,562,566,570,574,578,582,586,590,594,598,602,606,610,614,619,623,627,631,635,640,644,648,652,656,661,665,669,673,678],{"type":46,"tag":114,"props":550,"children":551},{"style":131},[552],{"type":52,"value":553},"REPO_ROOT",{"type":46,"tag":114,"props":555,"children":556},{"style":137},[557],{"type":52,"value":140},{"type":46,"tag":114,"props":559,"children":560},{"style":137},[561],{"type":52,"value":145},{"type":46,"tag":114,"props":563,"children":564},{"style":131},[565],{"type":52,"value":91},{"type":46,"tag":114,"props":567,"children":568},{"style":137},[569],{"type":52,"value":154},{"type":46,"tag":114,"props":571,"children":572},{"style":157},[573],{"type":52,"value":160},{"type":46,"tag":114,"props":575,"children":576},{"style":131},[577],{"type":52,"value":165},{"type":46,"tag":114,"props":579,"children":580},{"style":131},[581],{"type":52,"value":170},{"type":46,"tag":114,"props":583,"children":584},{"style":131},[585],{"type":52,"value":175},{"type":46,"tag":114,"props":587,"children":588},{"style":131},[589],{"type":52,"value":180},{"type":46,"tag":114,"props":591,"children":592},{"style":157},[593],{"type":52,"value":185},{"type":46,"tag":114,"props":595,"children":596},{"style":137},[597],{"type":52,"value":190},{"type":46,"tag":114,"props":599,"children":600},{"style":131},[601],{"type":52,"value":195},{"type":46,"tag":114,"props":603,"children":604},{"style":137},[605],{"type":52,"value":190},{"type":46,"tag":114,"props":607,"children":608},{"style":131},[609],{"type":52,"value":204},{"type":46,"tag":114,"props":611,"children":612},{"style":157},[613],{"type":52,"value":209},{"type":46,"tag":114,"props":615,"children":616},{"style":137},[617],{"type":52,"value":618},"}\"",{"type":46,"tag":114,"props":620,"children":621},{"style":137},[622],{"type":52,"value":425},{"type":46,"tag":114,"props":624,"children":625},{"style":137},[626],{"type":52,"value":229},{"type":46,"tag":114,"props":628,"children":629},{"style":137},[630],{"type":52,"value":239},{"type":46,"tag":114,"props":632,"children":633},{"style":137},[634],{"type":52,"value":244},{"type":46,"tag":114,"props":636,"children":637},{"style":131},[638],{"type":52,"value":639},"$REPO_ROOT",{"type":46,"tag":114,"props":641,"children":642},{"style":157},[643],{"type":52,"value":254},{"type":46,"tag":114,"props":645,"children":646},{"style":137},[647],{"type":52,"value":259},{"type":46,"tag":114,"props":649,"children":650},{"style":137},[651],{"type":52,"value":346},{"type":46,"tag":114,"props":653,"children":654},{"style":137},[655],{"type":52,"value":351},{"type":46,"tag":114,"props":657,"children":658},{"style":131},[659],{"type":52,"value":660}," REPO_ROOT",{"type":46,"tag":114,"props":662,"children":663},{"style":137},[664],{"type":52,"value":140},{"type":46,"tag":114,"props":666,"children":667},{"style":137},[668],{"type":52,"value":259},{"type":46,"tag":114,"props":670,"children":671},{"style":131},[672],{"type":52,"value":299},{"type":46,"tag":114,"props":674,"children":675},{"style":157},[676],{"type":52,"value":677},"\u002Fi4h-workflows",{"type":46,"tag":114,"props":679,"children":680},{"style":137},[681],{"type":52,"value":380},{"type":46,"tag":114,"props":683,"children":684},{"class":116,"line":127},[685,690,694],{"type":46,"tag":114,"props":686,"children":687},{"style":131},[688],{"type":52,"value":689},"ENV_ID",{"type":46,"tag":114,"props":691,"children":692},{"style":137},[693],{"type":52,"value":140},{"type":46,"tag":114,"props":695,"children":696},{"style":157},[697],{"type":52,"value":698},"scissor_pick_and_place\n",{"type":46,"tag":114,"props":700,"children":701},{"class":116,"line":217},[702,707,711,715,719,724,729],{"type":46,"tag":114,"props":703,"children":704},{"style":131},[705],{"type":52,"value":706},"RUNS_ROOT",{"type":46,"tag":114,"props":708,"children":709},{"style":137},[710],{"type":52,"value":140},{"type":46,"tag":114,"props":712,"children":713},{"style":137},[714],{"type":52,"value":145},{"type":46,"tag":114,"props":716,"children":717},{"style":131},[718],{"type":52,"value":553},{"type":46,"tag":114,"props":720,"children":721},{"style":137},[722],{"type":52,"value":723},"}",{"type":46,"tag":114,"props":725,"children":726},{"style":157},[727],{"type":52,"value":728},"\u002Fworkflows\u002Fagentic\u002Fruns",{"type":46,"tag":114,"props":730,"children":731},{"style":137},[732],{"type":52,"value":380},{"type":46,"tag":114,"props":734,"children":735},{"class":116,"line":272},[736,741,745,749,753,757,761,765],{"type":46,"tag":114,"props":737,"children":738},{"style":131},[739],{"type":52,"value":740},"EPISODE_INDEX",{"type":46,"tag":114,"props":742,"children":743},{"style":137},[744],{"type":52,"value":140},{"type":46,"tag":114,"props":746,"children":747},{"style":137},[748],{"type":52,"value":145},{"type":46,"tag":114,"props":750,"children":751},{"style":131},[752],{"type":52,"value":740},{"type":46,"tag":114,"props":754,"children":755},{"style":137},[756],{"type":52,"value":154},{"type":46,"tag":114,"props":758,"children":759},{"style":131},[760],{"type":52,"value":510},{"type":46,"tag":114,"props":762,"children":763},{"style":137},[764],{"type":52,"value":618},{"type":46,"tag":114,"props":766,"children":767},{"style":121},[768],{"type":52,"value":769},"  # For \"Replay second episode\", set EPISODE_INDEX=1.\n",{"type":46,"tag":114,"props":771,"children":772},{"class":116,"line":315},[773],{"type":46,"tag":114,"props":774,"children":776},{"emptyLinePlaceholder":775},true,[777],{"type":52,"value":778},"\n",{"type":46,"tag":114,"props":780,"children":781},{"class":116,"line":383},[782],{"type":46,"tag":114,"props":783,"children":784},{"style":121},[785],{"type":52,"value":786},"# Point HDF5_PATH at a real recording (absolute path). Recordings come from teleop, mimic, or\n",{"type":46,"tag":114,"props":788,"children":789},{"class":116,"line":392},[790],{"type":46,"tag":114,"props":791,"children":792},{"style":121},[793],{"type":52,"value":794},"# validate (which writes data\u002Fverify.hdf5 under each runs\u002Feval_* dir). List candidates newest-first:\n",{"type":46,"tag":114,"props":796,"children":798},{"class":116,"line":797},8,[799],{"type":46,"tag":114,"props":800,"children":801},{"style":121},[802],{"type":52,"value":803},"#   find \"${RUNS_ROOT}\" -name '*.hdf5' -printf '%TY-%Tm-%Td %TH:%TM  %p\\n' | sort -r | head\n",{"type":46,"tag":114,"props":805,"children":807},{"class":116,"line":806},9,[808,813,817,821,825],{"type":46,"tag":114,"props":809,"children":810},{"style":131},[811],{"type":52,"value":812},"HDF5_PATH",{"type":46,"tag":114,"props":814,"children":815},{"style":137},[816],{"type":52,"value":140},{"type":46,"tag":114,"props":818,"children":819},{"style":137},[820],{"type":52,"value":145},{"type":46,"tag":114,"props":822,"children":823},{"style":131},[824],{"type":52,"value":812},{"type":46,"tag":114,"props":826,"children":827},{"style":137},[828],{"type":52,"value":829},":-}\"\n",{"type":46,"tag":114,"props":831,"children":833},{"class":116,"line":832},10,[834,838,842,846,851,856,860,864,868],{"type":46,"tag":114,"props":835,"children":836},{"style":221},[837],{"type":52,"value":224},{"type":46,"tag":114,"props":839,"children":840},{"style":137},[841],{"type":52,"value":229},{"type":46,"tag":114,"props":843,"children":844},{"style":137},[845],{"type":52,"value":234},{"type":46,"tag":114,"props":847,"children":848},{"style":137},[849],{"type":52,"value":850}," -f",{"type":46,"tag":114,"props":852,"children":853},{"style":137},[854],{"type":52,"value":855}," \"${",{"type":46,"tag":114,"props":857,"children":858},{"style":131},[859],{"type":52,"value":812},{"type":46,"tag":114,"props":861,"children":862},{"style":137},[863],{"type":52,"value":618},{"type":46,"tag":114,"props":865,"children":866},{"style":137},[867],{"type":52,"value":264},{"type":46,"tag":114,"props":869,"children":870},{"style":221},[871],{"type":52,"value":269},{"type":46,"tag":114,"props":873,"children":875},{"class":116,"line":874},11,[876,881,885,890,895,899,903,908,913,917,921,926,930],{"type":46,"tag":114,"props":877,"children":878},{"style":428},[879],{"type":52,"value":880},"  echo",{"type":46,"tag":114,"props":882,"children":883},{"style":137},[884],{"type":52,"value":244},{"type":46,"tag":114,"props":886,"children":887},{"style":157},[888],{"type":52,"value":889},"replay: set HDF5_PATH to an existing .hdf5 (got '",{"type":46,"tag":114,"props":891,"children":892},{"style":137},[893],{"type":52,"value":894},"${",{"type":46,"tag":114,"props":896,"children":897},{"style":131},[898],{"type":52,"value":812},{"type":46,"tag":114,"props":900,"children":901},{"style":137},[902],{"type":52,"value":154},{"type":46,"tag":114,"props":904,"children":905},{"style":157},[906],{"type":52,"value":907},"\u003C",{"type":46,"tag":114,"props":909,"children":910},{"style":131},[911],{"type":52,"value":912},"unset",{"type":46,"tag":114,"props":914,"children":915},{"style":157},[916],{"type":52,"value":185},{"type":46,"tag":114,"props":918,"children":919},{"style":137},[920],{"type":52,"value":723},{"type":46,"tag":114,"props":922,"children":923},{"style":157},[924],{"type":52,"value":925},"'). Candidates:",{"type":46,"tag":114,"props":927,"children":928},{"style":137},[929],{"type":52,"value":259},{"type":46,"tag":114,"props":931,"children":932},{"style":137},[933],{"type":52,"value":934}," >&2\n",{"type":46,"tag":114,"props":936,"children":938},{"class":116,"line":937},12,[939,944,948,952,956,961,966,971,976,981,985,990,994,999,1004,1009,1014,1019,1023],{"type":46,"tag":114,"props":940,"children":941},{"style":354},[942],{"type":52,"value":943},"  find",{"type":46,"tag":114,"props":945,"children":946},{"style":137},[947],{"type":52,"value":855},{"type":46,"tag":114,"props":949,"children":950},{"style":131},[951],{"type":52,"value":706},{"type":46,"tag":114,"props":953,"children":954},{"style":137},[955],{"type":52,"value":618},{"type":46,"tag":114,"props":957,"children":958},{"style":157},[959],{"type":52,"value":960}," -name",{"type":46,"tag":114,"props":962,"children":963},{"style":137},[964],{"type":52,"value":965}," '",{"type":46,"tag":114,"props":967,"children":968},{"style":157},[969],{"type":52,"value":970},"*.hdf5",{"type":46,"tag":114,"props":972,"children":973},{"style":137},[974],{"type":52,"value":975},"'",{"type":46,"tag":114,"props":977,"children":978},{"style":157},[979],{"type":52,"value":980}," -printf",{"type":46,"tag":114,"props":982,"children":983},{"style":137},[984],{"type":52,"value":965},{"type":46,"tag":114,"props":986,"children":987},{"style":157},[988],{"type":52,"value":989},"%TY-%Tm-%Td %TH:%TM  %p\\n",{"type":46,"tag":114,"props":991,"children":992},{"style":137},[993],{"type":52,"value":975},{"type":46,"tag":114,"props":995,"children":996},{"style":137},[997],{"type":52,"value":998}," 2>",{"type":46,"tag":114,"props":1000,"children":1001},{"style":157},[1002],{"type":52,"value":1003},"\u002Fdev\u002Fnull",{"type":46,"tag":114,"props":1005,"children":1006},{"style":137},[1007],{"type":52,"value":1008}," |",{"type":46,"tag":114,"props":1010,"children":1011},{"style":354},[1012],{"type":52,"value":1013}," sort",{"type":46,"tag":114,"props":1015,"children":1016},{"style":157},[1017],{"type":52,"value":1018}," -r",{"type":46,"tag":114,"props":1020,"children":1021},{"style":137},[1022],{"type":52,"value":1008},{"type":46,"tag":114,"props":1024,"children":1025},{"style":354},[1026],{"type":52,"value":1027}," head\n",{"type":46,"tag":114,"props":1029,"children":1031},{"class":116,"line":1030},13,[1032,1037],{"type":46,"tag":114,"props":1033,"children":1034},{"style":428},[1035],{"type":52,"value":1036},"  exit",{"type":46,"tag":114,"props":1038,"children":1040},{"style":1039},"--shiki-light:#F76D47;--shiki-default:#F78C6C;--shiki-dark:#F78C6C",[1041],{"type":52,"value":1042}," 1\n",{"type":46,"tag":114,"props":1044,"children":1046},{"class":116,"line":1045},14,[1047],{"type":46,"tag":114,"props":1048,"children":1049},{"style":221},[1050],{"type":52,"value":389},{"type":46,"tag":114,"props":1052,"children":1054},{"class":116,"line":1053},15,[1055],{"type":46,"tag":114,"props":1056,"children":1057},{"emptyLinePlaceholder":775},[1058],{"type":52,"value":778},{"type":46,"tag":114,"props":1060,"children":1062},{"class":116,"line":1061},16,[1063,1068,1072,1076,1080,1084,1089,1093,1097,1101,1106,1110,1115,1120],{"type":46,"tag":114,"props":1064,"children":1065},{"style":131},[1066],{"type":52,"value":1067},"RUN_DIR",{"type":46,"tag":114,"props":1069,"children":1070},{"style":137},[1071],{"type":52,"value":140},{"type":46,"tag":114,"props":1073,"children":1074},{"style":137},[1075],{"type":52,"value":145},{"type":46,"tag":114,"props":1077,"children":1078},{"style":131},[1079],{"type":52,"value":706},{"type":46,"tag":114,"props":1081,"children":1082},{"style":137},[1083],{"type":52,"value":723},{"type":46,"tag":114,"props":1085,"children":1086},{"style":157},[1087],{"type":52,"value":1088},"\u002Freplay_",{"type":46,"tag":114,"props":1090,"children":1091},{"style":137},[1092],{"type":52,"value":894},{"type":46,"tag":114,"props":1094,"children":1095},{"style":131},[1096],{"type":52,"value":689},{"type":46,"tag":114,"props":1098,"children":1099},{"style":137},[1100],{"type":52,"value":723},{"type":46,"tag":114,"props":1102,"children":1103},{"style":157},[1104],{"type":52,"value":1105},"_",{"type":46,"tag":114,"props":1107,"children":1108},{"style":137},[1109],{"type":52,"value":160},{"type":46,"tag":114,"props":1111,"children":1112},{"style":354},[1113],{"type":52,"value":1114},"date",{"type":46,"tag":114,"props":1116,"children":1117},{"style":157},[1118],{"type":52,"value":1119}," +%Y%m%d_%H%M%S",{"type":46,"tag":114,"props":1121,"children":1122},{"style":137},[1123],{"type":52,"value":1124},")\"\n",{"type":46,"tag":114,"props":1126,"children":1128},{"class":116,"line":1127},17,[1129,1134,1139,1143,1147,1151,1156],{"type":46,"tag":114,"props":1130,"children":1131},{"style":354},[1132],{"type":52,"value":1133},"mkdir",{"type":46,"tag":114,"props":1135,"children":1136},{"style":157},[1137],{"type":52,"value":1138}," -p",{"type":46,"tag":114,"props":1140,"children":1141},{"style":137},[1142],{"type":52,"value":855},{"type":46,"tag":114,"props":1144,"children":1145},{"style":131},[1146],{"type":52,"value":1067},{"type":46,"tag":114,"props":1148,"children":1149},{"style":137},[1150],{"type":52,"value":723},{"type":46,"tag":114,"props":1152,"children":1153},{"style":157},[1154],{"type":52,"value":1155},"\u002Flogs",{"type":46,"tag":114,"props":1157,"children":1158},{"style":137},[1159],{"type":52,"value":380},{"type":46,"tag":114,"props":1161,"children":1163},{"class":116,"line":1162},18,[1164,1169,1174,1178,1182,1186,1190,1194,1198,1203],{"type":46,"tag":114,"props":1165,"children":1166},{"style":354},[1167],{"type":52,"value":1168},"ln",{"type":46,"tag":114,"props":1170,"children":1171},{"style":157},[1172],{"type":52,"value":1173}," -sfn",{"type":46,"tag":114,"props":1175,"children":1176},{"style":137},[1177],{"type":52,"value":855},{"type":46,"tag":114,"props":1179,"children":1180},{"style":131},[1181],{"type":52,"value":1067},{"type":46,"tag":114,"props":1183,"children":1184},{"style":137},[1185],{"type":52,"value":618},{"type":46,"tag":114,"props":1187,"children":1188},{"style":137},[1189],{"type":52,"value":855},{"type":46,"tag":114,"props":1191,"children":1192},{"style":131},[1193],{"type":52,"value":706},{"type":46,"tag":114,"props":1195,"children":1196},{"style":137},[1197],{"type":52,"value":723},{"type":46,"tag":114,"props":1199,"children":1200},{"style":157},[1201],{"type":52,"value":1202},"\u002F.latest",{"type":46,"tag":114,"props":1204,"children":1205},{"style":137},[1206],{"type":52,"value":380},{"type":46,"tag":533,"props":1208,"children":1210},{"id":1209},"step-2-replay",[1211],{"type":52,"value":1212},"Step 2 — replay",{"type":46,"tag":103,"props":1214,"children":1216},{"className":105,"code":1215,"language":107,"meta":108,"style":108},"\"${REPO_ROOT}\u002Fworkflows\u002Fagentic\u002Farena\u002Frun.sh\" \\\n  --env \"${ENV_ID}\" \\\n  --replay \"${HDF5_PATH}\" \\\n  --episode-index \"${EPISODE_INDEX}\" \\\n  2>&1 | tee \"${RUN_DIR}\u002Flogs\u002Freplay.log\"\n",[1217],{"type":46,"tag":78,"props":1218,"children":1219},{"__ignoreMap":108},[1220,1249,1273,1297,1321],{"type":46,"tag":114,"props":1221,"children":1222},{"class":116,"line":117},[1223,1227,1231,1235,1239,1244],{"type":46,"tag":114,"props":1224,"children":1225},{"style":354},[1226],{"type":52,"value":259},{"type":46,"tag":114,"props":1228,"children":1229},{"style":137},[1230],{"type":52,"value":894},{"type":46,"tag":114,"props":1232,"children":1233},{"style":131},[1234],{"type":52,"value":553},{"type":46,"tag":114,"props":1236,"children":1237},{"style":137},[1238],{"type":52,"value":723},{"type":46,"tag":114,"props":1240,"children":1241},{"style":354},[1242],{"type":52,"value":1243},"\u002Fworkflows\u002Fagentic\u002Farena\u002Frun.sh\"",{"type":46,"tag":114,"props":1245,"children":1246},{"style":131},[1247],{"type":52,"value":1248}," \\\n",{"type":46,"tag":114,"props":1250,"children":1251},{"class":116,"line":127},[1252,1257,1261,1265,1269],{"type":46,"tag":114,"props":1253,"children":1254},{"style":157},[1255],{"type":52,"value":1256},"  --env",{"type":46,"tag":114,"props":1258,"children":1259},{"style":137},[1260],{"type":52,"value":855},{"type":46,"tag":114,"props":1262,"children":1263},{"style":131},[1264],{"type":52,"value":689},{"type":46,"tag":114,"props":1266,"children":1267},{"style":137},[1268],{"type":52,"value":618},{"type":46,"tag":114,"props":1270,"children":1271},{"style":131},[1272],{"type":52,"value":1248},{"type":46,"tag":114,"props":1274,"children":1275},{"class":116,"line":217},[1276,1281,1285,1289,1293],{"type":46,"tag":114,"props":1277,"children":1278},{"style":157},[1279],{"type":52,"value":1280},"  --replay",{"type":46,"tag":114,"props":1282,"children":1283},{"style":137},[1284],{"type":52,"value":855},{"type":46,"tag":114,"props":1286,"children":1287},{"style":131},[1288],{"type":52,"value":812},{"type":46,"tag":114,"props":1290,"children":1291},{"style":137},[1292],{"type":52,"value":618},{"type":46,"tag":114,"props":1294,"children":1295},{"style":131},[1296],{"type":52,"value":1248},{"type":46,"tag":114,"props":1298,"children":1299},{"class":116,"line":272},[1300,1305,1309,1313,1317],{"type":46,"tag":114,"props":1301,"children":1302},{"style":157},[1303],{"type":52,"value":1304},"  --episode-index",{"type":46,"tag":114,"props":1306,"children":1307},{"style":137},[1308],{"type":52,"value":855},{"type":46,"tag":114,"props":1310,"children":1311},{"style":131},[1312],{"type":52,"value":740},{"type":46,"tag":114,"props":1314,"children":1315},{"style":137},[1316],{"type":52,"value":618},{"type":46,"tag":114,"props":1318,"children":1319},{"style":131},[1320],{"type":52,"value":1248},{"type":46,"tag":114,"props":1322,"children":1323},{"class":116,"line":315},[1324,1329,1333,1338,1342,1346,1350,1355],{"type":46,"tag":114,"props":1325,"children":1326},{"style":137},[1327],{"type":52,"value":1328},"  2>&1",{"type":46,"tag":114,"props":1330,"children":1331},{"style":137},[1332],{"type":52,"value":1008},{"type":46,"tag":114,"props":1334,"children":1335},{"style":354},[1336],{"type":52,"value":1337}," tee",{"type":46,"tag":114,"props":1339,"children":1340},{"style":137},[1341],{"type":52,"value":855},{"type":46,"tag":114,"props":1343,"children":1344},{"style":131},[1345],{"type":52,"value":1067},{"type":46,"tag":114,"props":1347,"children":1348},{"style":137},[1349],{"type":52,"value":723},{"type":46,"tag":114,"props":1351,"children":1352},{"style":157},[1353],{"type":52,"value":1354},"\u002Flogs\u002Freplay.log",{"type":46,"tag":114,"props":1356,"children":1357},{"style":137},[1358],{"type":52,"value":380},{"type":46,"tag":55,"props":1360,"children":1362},{"id":1361},"notes",[1363],{"type":52,"value":1364},"Notes",{"type":46,"tag":451,"props":1366,"children":1367},{},[1368,1394,1423,1434,1446],{"type":46,"tag":455,"props":1369,"children":1370},{},[1371,1376,1378,1384,1386,1392],{"type":46,"tag":78,"props":1372,"children":1374},{"className":1373},[],[1375],{"type":52,"value":812},{"type":52,"value":1377}," must be an absolute path to an existing recording — ",{"type":46,"tag":78,"props":1379,"children":1381},{"className":1380},[],[1382],{"type":52,"value":1383},"--replay",{"type":52,"value":1385}," resolves a relative path against ",{"type":46,"tag":78,"props":1387,"children":1389},{"className":1388},[],[1390],{"type":52,"value":1391},"runs\u002F\u003Cenv>\u002F",{"type":52,"value":1393},", not your cwd, so a bare\u002Frelative path silently fails to load. The block lists real candidates if it's unset or wrong.",{"type":46,"tag":455,"props":1395,"children":1396},{},[1397,1399,1405,1407,1413,1415,1421],{"type":52,"value":1398},"Recordings come from [[i4h-workflow-dataset-teleop]], [[i4h-workflow-dataset-mimic]], or [[i4h-workflow-validate]] (validate writes ",{"type":46,"tag":78,"props":1400,"children":1402},{"className":1401},[],[1403],{"type":52,"value":1404},"data\u002Fverify.hdf5",{"type":52,"value":1406}," under each ",{"type":46,"tag":78,"props":1408,"children":1410},{"className":1409},[],[1411],{"type":52,"value":1412},"runs\u002Feval_*",{"type":52,"value":1414}," dir). There is no default ",{"type":46,"tag":78,"props":1416,"children":1418},{"className":1417},[],[1419],{"type":52,"value":1420},"demo.hdf5",{"type":52,"value":1422},".",{"type":46,"tag":455,"props":1424,"children":1425},{},[1426,1432],{"type":46,"tag":78,"props":1427,"children":1429},{"className":1428},[],[1430],{"type":52,"value":1431},"--episode-index",{"type":52,"value":1433}," selects the episode within the HDF5 (zero-based).",{"type":46,"tag":455,"props":1435,"children":1436},{},[1437,1439,1445],{"type":52,"value":1438},"For \"Replay second episode\", use ",{"type":46,"tag":78,"props":1440,"children":1442},{"className":1441},[],[1443],{"type":52,"value":1444},"--episode-index 1",{"type":52,"value":1422},{"type":46,"tag":455,"props":1447,"children":1448},{},[1449],{"type":52,"value":1450},"Use the same env id as the env that produced the recording.",{"type":46,"tag":55,"props":1452,"children":1454},{"id":1453},"prerequisites",[1455],{"type":52,"value":1456},"Prerequisites",{"type":46,"tag":451,"props":1458,"children":1459},{},[1460,1473,1478],{"type":46,"tag":455,"props":1461,"children":1462},{},[1463,1465,1471],{"type":52,"value":1464},"Workflow set up via [[i4h-workflow-setup]] (the ",{"type":46,"tag":78,"props":1466,"children":1468},{"className":1467},[],[1469],{"type":52,"value":1470},".venv",{"type":52,"value":1472}," must exist).",{"type":46,"tag":455,"props":1474,"children":1475},{},[1476],{"type":52,"value":1477},"An existing HDF5 recording to replay.",{"type":46,"tag":455,"props":1479,"children":1480},{},[1481],{"type":52,"value":1482},"The env id that produced the recording.",{"type":46,"tag":55,"props":1484,"children":1486},{"id":1485},"limitations",[1487],{"type":52,"value":1488},"Limitations",{"type":46,"tag":451,"props":1490,"children":1491},{},[1492,1497,1508],{"type":46,"tag":455,"props":1493,"children":1494},{},[1495],{"type":52,"value":1496},"Visual verification only; replay does not modify or expand the recording.",{"type":46,"tag":455,"props":1498,"children":1499},{},[1500,1502,1507],{"type":52,"value":1501},"Replays one episode per invocation, selected by ",{"type":46,"tag":78,"props":1503,"children":1505},{"className":1504},[],[1506],{"type":52,"value":1431},{"type":52,"value":1422},{"type":46,"tag":455,"props":1509,"children":1510},{},[1511],{"type":52,"value":1512},"Runs inside Isaac Sim; the env id must match the one that produced the HDF5.",{"type":46,"tag":55,"props":1514,"children":1516},{"id":1515},"troubleshooting",[1517],{"type":52,"value":1518},"Troubleshooting",{"type":46,"tag":451,"props":1520,"children":1521},{},[1522,1538,1577,1593],{"type":46,"tag":455,"props":1523,"children":1524},{},[1525,1530,1531,1536],{"type":46,"tag":459,"props":1526,"children":1527},{},[1528],{"type":52,"value":1529},"Error:",{"type":52,"value":465},{"type":46,"tag":78,"props":1532,"children":1534},{"className":1533},[],[1535],{"type":52,"value":1470},{"type":52,"value":1537}," not found \u002F replay fails to launch - Cause: workflow not set up. Fix: run [[i4h-workflow-setup]] first.",{"type":46,"tag":455,"props":1539,"children":1540},{},[1541,1545,1546,1552,1554,1559,1561,1567,1569,1575],{"type":46,"tag":459,"props":1542,"children":1543},{},[1544],{"type":52,"value":1529},{"type":52,"value":465},{"type":46,"tag":78,"props":1547,"children":1549},{"className":1548},[],[1550],{"type":52,"value":1551},"replay: set HDF5_PATH to an existing .hdf5",{"type":52,"value":1553}," (or recording fails to load) - Cause: ",{"type":46,"tag":78,"props":1555,"children":1557},{"className":1556},[],[1558],{"type":52,"value":812},{"type":52,"value":1560}," unset or not a real file. Fix: pick an absolute path from the printed candidates (e.g. a ",{"type":46,"tag":78,"props":1562,"children":1564},{"className":1563},[],[1565],{"type":52,"value":1566},"verify.hdf5",{"type":52,"value":1568}," under ",{"type":46,"tag":78,"props":1570,"children":1572},{"className":1571},[],[1573],{"type":52,"value":1574},"runs\u002Feval_*\u002Fdata\u002F",{"type":52,"value":1576},").",{"type":46,"tag":455,"props":1578,"children":1579},{},[1580,1584,1586,1591],{"type":46,"tag":459,"props":1581,"children":1582},{},[1583],{"type":52,"value":1529},{"type":52,"value":1585}," episode index out of range - Cause: ",{"type":46,"tag":78,"props":1587,"children":1589},{"className":1588},[],[1590],{"type":52,"value":1431},{"type":52,"value":1592}," exceeds the episodes in the HDF5. Fix: use a valid zero-based index.",{"type":46,"tag":455,"props":1594,"children":1595},{},[1596,1600,1602,1608],{"type":46,"tag":459,"props":1597,"children":1598},{},[1599],{"type":52,"value":1529},{"type":52,"value":1601}," mismatched\u002Fgarbled playback - Cause: ",{"type":46,"tag":78,"props":1603,"children":1605},{"className":1604},[],[1606],{"type":52,"value":1607},"--env",{"type":52,"value":1609}," differs from the env that produced the recording. Fix: use the same env id.",{"type":46,"tag":55,"props":1611,"children":1613},{"id":1612},"final-response",[1614],{"type":52,"value":1615},"Final Response",{"type":46,"tag":62,"props":1617,"children":1618},{},[1619],{"type":52,"value":1620},"Report env, HDF5 path, episode index, launch outcome, visible mismatches.",{"type":46,"tag":1622,"props":1623,"children":1624},"style",{},[1625],{"type":52,"value":1626},"html .light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html.light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html .default .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}html.dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}",{"items":1628,"total":1787},[1629,1647,1665,1676,1688,1702,1715,1729,1742,1753,1767,1776],{"slug":1630,"name":1630,"fn":1631,"description":1632,"org":1633,"tags":1634,"stars":1644,"repoUrl":1645,"updatedAt":1646},"nemoclaw-user-guide","retrieve NemoClaw documentation and configuration","Guides human users' AI agents to the NemoClaw docs MCP server and canonical Fern documentation in Markdown form. Use when users ask how to install, configure, operate, troubleshoot, secure, or learn NemoClaw with an AI coding assistant. Trigger keywords - nemoclaw docs, use nemoclaw with ai agent, nemoclaw mcp docs, nemoclaw install help, nemoclaw quickstart, nemoclaw markdown docs, llms.txt, agent skills.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1635,1638,1641],{"name":1636,"slug":1637,"type":15},"Documentation","documentation",{"name":1639,"slug":1640,"type":15},"MCP","mcp",{"name":1642,"slug":1643,"type":15},"Search","search",21777,"https:\u002F\u002Fgithub.com\u002FNVIDIA\u002FNemoClaw","2026-07-20T06:00:01.461044",{"slug":1648,"name":1648,"fn":1649,"description":1650,"org":1651,"tags":1652,"stars":1662,"repoUrl":1663,"updatedAt":1664},"mcore-build-and-dependency","manage Megatron-LM development environments","Container-based dev environment setup and dependency management for Megatron-LM. Covers acquiring and launching the CI container, uv package management, and updating uv.lock.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1653,1656,1659],{"name":1654,"slug":1655,"type":15},"Containers","containers",{"name":1657,"slug":1658,"type":15},"Deployment","deployment",{"name":1660,"slug":1661,"type":15},"Python","python",17049,"https:\u002F\u002Fgithub.com\u002FNVIDIA\u002FMegatron-LM","2026-07-27T06:06:11.249662",{"slug":1666,"name":1666,"fn":1667,"description":1668,"org":1669,"tags":1670,"stars":1662,"repoUrl":1663,"updatedAt":1675},"mcore-bump-base-image","update NVIDIA PyTorch base images","Bump the NVIDIA PyTorch base image (`nvcr.io\u002Fnvidia\u002Fpytorch:YY.MM-py3`) used by Megatron-LM CI. Covers the two pin sites (GitHub CI in `docker\u002F.ngc_version.dev` and GitLab CI in `.gitlab\u002Fstages\u002F01.build.yml`), the post-bump CI loop (re-run functional tests, refresh golden values, mark broken tests), and the gotchas that bit PRs",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1671,1674],{"name":1672,"slug":1673,"type":15},"CI\u002FCD","ci-cd",{"name":1657,"slug":1658,"type":15},"2026-07-14T05:25:59.97109",{"slug":1677,"name":1677,"fn":1678,"description":1679,"org":1680,"tags":1681,"stars":1662,"repoUrl":1663,"updatedAt":1687},"mcore-cicd","manage CI\u002FCD pipelines for Megatron-LM","CI\u002FCD reference for Megatron-LM. Covers CI pipeline structure, PR scope labels, triggering internal GitLab CI (which force-pushes the current branch to a pull-request\u002FBRANCH ref — always dry-run and verify the destination first; never run against shared or protected branches), and CI failure investigation.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1682,1683,1684],{"name":1672,"slug":1673,"type":15},{"name":1657,"slug":1658,"type":15},{"name":1685,"slug":1686,"type":15},"GitHub","github","2026-07-27T06:06:12.278222",{"slug":1689,"name":1689,"fn":1690,"description":1691,"org":1692,"tags":1693,"stars":1662,"repoUrl":1663,"updatedAt":1701},"mcore-create-issue","investigate CI failures and create issues","Investigate a failing GitHub Actions run or job and create a GitHub issue for the failure.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1694,1697,1698],{"name":1695,"slug":1696,"type":15},"Debugging","debugging",{"name":1685,"slug":1686,"type":15},{"name":1699,"slug":1700,"type":15},"Triage","triage","2026-07-14T05:25:57.442089",{"slug":1703,"name":1703,"fn":1704,"description":1705,"org":1706,"tags":1707,"stars":1662,"repoUrl":1663,"updatedAt":1714},"mcore-linting-and-formatting","lint and format Megatron-LM code","Linting and formatting for Megatron-LM. Covers running autoformat.sh, tools (ruff, black, isort, pylint, mypy), and code style rules.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1708,1711],{"name":1709,"slug":1710,"type":15},"Best Practices","best-practices",{"name":1712,"slug":1713,"type":15},"Code Analysis","code-analysis","2026-07-14T05:25:56.18433",{"slug":1716,"name":1716,"fn":1717,"description":1718,"org":1719,"tags":1720,"stars":1662,"repoUrl":1663,"updatedAt":1728},"mcore-migrate-gpt-to-hybrid","migrate Megatron-LM models to HybridModel","Migration guide for moving Megatron Core GPTModel checkpoints, model providers, training commands, and layer mappings to HybridModel.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1721,1724,1727],{"name":1722,"slug":1723,"type":15},"Machine Learning","machine-learning",{"name":1725,"slug":1726,"type":15},"Migration","migration",{"name":9,"slug":8,"type":15},"2026-07-17T06:07:11.777011",{"slug":1730,"name":1730,"fn":1731,"description":1732,"org":1733,"tags":1734,"stars":1662,"repoUrl":1663,"updatedAt":1741},"mcore-onboard-gb200-1node-tests","onboard functional tests for GB200","Onboard 1-node GitHub MR functional tests for GB200 from existing mr-scoped 2-node tests.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1735,1738],{"name":1736,"slug":1737,"type":15},"QA","qa",{"name":1739,"slug":1740,"type":15},"Testing","testing","2026-07-14T05:25:53.673039",{"slug":1743,"name":1743,"fn":1744,"description":1745,"org":1746,"tags":1747,"stars":1662,"repoUrl":1663,"updatedAt":1752},"mcore-run-on-slurm","launch distributed training jobs on SLURM","How to launch distributed Megatron-LM training jobs on a SLURM cluster. Covers a minimal sbatch skeleton, environment-variable setup for torch.distributed.run, CUDA_DEVICE_MAX_CONNECTIONS rules across hardware and parallelism modes, container conventions, monitoring, and per-rank failure diagnosis.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1748,1749],{"name":1657,"slug":1658,"type":15},{"name":1750,"slug":1751,"type":15},"Infrastructure","infrastructure","2026-07-14T05:25:49.362534",{"slug":1754,"name":1754,"fn":1755,"description":1756,"org":1757,"tags":1758,"stars":1662,"repoUrl":1663,"updatedAt":1766},"mcore-split-pr","split pull requests to reduce review load","Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1759,1762,1763],{"name":1760,"slug":1761,"type":15},"Code Review","code-review",{"name":1685,"slug":1686,"type":15},{"name":1764,"slug":1765,"type":15},"Pull Requests","pull-requests","2026-07-14T05:26:01.226578",{"slug":1768,"name":1768,"fn":1769,"description":1770,"org":1771,"tags":1772,"stars":1662,"repoUrl":1663,"updatedAt":1775},"mcore-testing","run and manage Megatron-LM tests","Test system for Megatron-LM. Covers test layout, recipe YAML structure, adding and running unit and functional tests, golden values, marker filters, and CI parity.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1773,1774],{"name":1736,"slug":1737,"type":15},{"name":1739,"slug":1740,"type":15},"2026-07-14T05:25:54.928983",{"slug":1777,"name":1777,"fn":1778,"description":1779,"org":1780,"tags":1781,"stars":1662,"repoUrl":1663,"updatedAt":1786},"nightly-sync","manage nightly main-to-dev sync workflows","Domain knowledge for the nightly main-to-dev sync workflow. Covers merge strategy, CI architecture, failure investigation, and known issues.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1782,1785],{"name":1783,"slug":1784,"type":15},"Automation","automation",{"name":1672,"slug":1673,"type":15},"2026-07-30T05:29:03.275638",496,{"items":1789,"total":1883},[1790,1807,1817,1831,1841,1856,1871],{"slug":1791,"name":1791,"fn":1792,"description":1793,"org":1794,"tags":1795,"stars":20,"repoUrl":21,"updatedAt":1806},"accelerated-computing-cudf","accelerate data processing with cuDF","Official NVIDIA-authored guidance for NVIDIA cuDF GPU DataFrames, pandas acceleration, dask-cuDF, ETL, joins, groupby, CSV\u002FParquet I\u002FO, nullable semantics, and multi-GPU DataFrame workloads.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1796,1799,1802,1803],{"name":1797,"slug":1798,"type":15},"Data Analysis","data-analysis",{"name":1800,"slug":1801,"type":15},"Data Engineering","data-engineering",{"name":9,"slug":8,"type":15},{"name":1804,"slug":1805,"type":15},"Performance","performance","2026-07-14T05:28:43.176466",{"slug":1808,"name":1808,"fn":1809,"description":1810,"org":1811,"tags":1812,"stars":20,"repoUrl":21,"updatedAt":1816},"aiq-deploy","deploy and manage NVIDIA AI-Q infrastructure","Use when asked to install, deploy, run, validate, troubleshoot, or stop NVIDIA AI-Q Blueprint infrastructure.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1813,1814,1815],{"name":1657,"slug":1658,"type":15},{"name":1750,"slug":1751,"type":15},{"name":9,"slug":8,"type":15},"2026-07-14T05:29:06.667109",{"slug":1818,"name":1818,"fn":1819,"description":1820,"org":1821,"tags":1822,"stars":20,"repoUrl":21,"updatedAt":1830},"aiq-research","conduct deep research with AI-Q","Use when asked to run deep research or AI-Q research through a reachable NVIDIA AI-Q Blueprint backend.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1823,1826,1827],{"name":1824,"slug":1825,"type":15},"Agents","agents",{"name":9,"slug":8,"type":15},{"name":1828,"slug":1829,"type":15},"Research","research","2026-07-14T05:28:06.816956",{"slug":1832,"name":1832,"fn":1833,"description":1834,"org":1835,"tags":1836,"stars":20,"repoUrl":21,"updatedAt":1840},"amc-run-sample-calibration","run AMC sample dataset calibration","Run end-to-end calibration on the shipped sample dataset (sdg_08_2_sample_data_010926.zip) against a running AMC microservice. Use when user says 'test sample dataset', 'run sample calibration', 'verify AMC install', or 'launch and test'.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1837,1838,1839],{"name":1797,"slug":1798,"type":15},{"name":9,"slug":8,"type":15},{"name":1739,"slug":1740,"type":15},"2026-07-17T05:29:03.913266",{"slug":1842,"name":1842,"fn":1843,"description":1844,"org":1845,"tags":1846,"stars":20,"repoUrl":21,"updatedAt":1855},"amc-run-video-calibration","calibrate video datasets with AutoMagicCalib","Calibrate a new dataset from pre-recorded video files via the AutoMagicCalib REST API. Use when user has local MP4s and says 'calibrate my videos', 'run AMC on these videos', or similar. For RTSP\u002Flive streams, use amc-run-rtsp-calibration instead.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1847,1848,1851,1852],{"name":1783,"slug":1784,"type":15},{"name":1849,"slug":1850,"type":15},"Imaging","imaging",{"name":9,"slug":8,"type":15},{"name":1853,"slug":1854,"type":15},"Video","video","2026-07-17T05:28:53.905004",{"slug":1857,"name":1857,"fn":1858,"description":1859,"org":1860,"tags":1861,"stars":20,"repoUrl":21,"updatedAt":1870},"amc-setup-calibration-stack","deploy AutoMagicCalib microservice with Docker","Launch AutoMagicCalib microservice and web UI from NGC release images via Docker Compose. Use when user says 'deploy auto calibration', 'launch auto calibration', 'launch AMC', 'start MS+UI', or 'set up auto-magic-calib'. Requires NGC API key.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1862,1863,1866,1867],{"name":1657,"slug":1658,"type":15},{"name":1864,"slug":1865,"type":15},"Docker","docker",{"name":9,"slug":8,"type":15},{"name":1868,"slug":1869,"type":15},"Operations","operations","2026-07-17T05:28:56.913999",{"slug":1872,"name":1872,"fn":1873,"description":1874,"org":1875,"tags":1876,"stars":20,"repoUrl":21,"updatedAt":1882},"cudaq-guide","develop quantum applications with CUDA-Q","CUDA-Q onboarding guide for installation, test programs, GPU simulation, QPU hardware, and quantum applications.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[1877,1878,1881],{"name":9,"slug":8,"type":15},{"name":1879,"slug":1880,"type":15},"Quantum Computing","quantum-computing",{"name":18,"slug":19,"type":15},"2026-07-14T05:26:58.898253",305]