{
  "skills": ["vss-deploy-dense-captioning", "vss-deploy-profile"],
  "profile": "alerts",
  "deploy_mode": "real-time",
  "resources": {
    "platforms": {
      "L40S": {
        "modes": ["remote-all"]
      }
    }
  },
  "env": "A GPU host matching `{{platform}}` with Docker + NVIDIA Container Toolkit, `NGC_CLI_API_KEY`, and remote LLM/VLM endpoint env vars (`LLM_REMOTE_URL`, `LLM_REMOTE_MODEL`, `VLM_REMOTE_URL`, `VLM_REMOTE_MODEL`). The eval harness predeploys the full VSS `alerts` profile in `real-time` mode with remote LLM + remote VLM placement before this task starts; this task tests the RT-VLM microservice directly at http://localhost:8018. Required after predeploy: `rtvi-vlm` healthy on port 8018, `mdx-kafka` running, source-backed RT-VLM Kafka topics visible in the live container env (`KAFKA_TOPIC=mdx-vlm`, `KAFKA_INCIDENT_TOPIC=mdx-vlm-incidents`, `ERROR_MESSAGE_TOPIC=vision-llm-errors` unless the deployment explicitly overrides them), and the public NVIDIA RTSP sample stream reachable from the host. Precheck the stream with `ffprobe`, `gst-discoverer-1.0`, or an equivalent RTSP probe before registering it, and require the probe to discover a video stream/caps entry.",
  "expects": [
    {
      "query": "The VSS alerts profile is already deployed in real-time mode on {{platform}} with remote LLM and remote VLM endpoints by the eval harness. Use the `/vss-deploy-dense-captioning` skill to test RT-VLM directly at http://localhost:8018: verify readiness, models, `/openapi.json`, `/v1/assets/stats`, text-only `/v1/chat/completions`, and the current 26.05 legacy `/v1/completions` HTTP 400 behavior. Do not call `/v1/license` unless the live OpenAPI exposes it; report it as absent if missing. Precheck the RTSP sample stream with `ffprobe`, `gst-discoverer-1.0`, or an equivalent RTSP probe and fail fast with a clear message if it is unreachable or reports an unknown/non-video media type, register a temporary RTSP stream with description `rt-vlm-eval-{{mode}}` and URL `rtsp://nv-wowza-pdc.nvidia.com:1935/vod/warehouse_1.mp4`, delete that temporary stream, confirm `KAFKA_INCIDENT_TOPIC` from the live RT-VLM container env, and show the Kafka incident-consumer command using the VSS Kafka container. Run autonomously and clean up before your final reply.",
      "checks": [
        "The agent treated the VSS `alerts` profile in `real-time` mode as already deployed by the eval harness and did not invoke `/vss-deploy-profile` or `scripts/dev-profile.sh` during this task.",
        "`curl -sf --max-time 15 http://localhost:8018/v1/health/ready` returns exit 0.",
        "`curl -sf --max-time 15 http://localhost:8018/v1/models` returns exit 0 and returns JSON with a non-empty model list or model metadata.",
        "`curl -sf --max-time 15 http://localhost:8018/openapi.json` returns exit 0 and the agent used it as the endpoint source of truth.",
        "`curl -sf --max-time 15 http://localhost:8018/v1/assets/stats` returns exit 0 when exposed by the live OpenAPI, or the agent clearly reports that the live OpenAPI omitted it.",
        "The agent did not present `/v1/license` as supported unless `/openapi.json` listed it; on current 26.05 builds it should report that `/v1/license` is absent/404.",
        "The agent successfully called text-only `POST http://localhost:8018/v1/chat/completions` with a messages array and model.",
        "The agent called text-only `POST http://localhost:8018/v1/completions` only to verify the documented legacy behavior, and treated HTTP 400 as expected on current 26.05 builds.",
        "`docker ps --format '{{.Names}}' | grep -qx vss-rtvi-vlm` returns exit 0.",
        "`docker ps --format '{{.Names}}' | grep -qx mdx-kafka` returns exit 0.",
        "The agent prechecked `rtsp://nv-wowza-pdc.nvidia.com:1935/vod/warehouse_1.mp4` with `ffprobe`, `gst-discoverer-1.0`, or an equivalent RTSP probe before calling `/v1/streams/add`, verified the probe discovered a video stream/caps entry, and would fail fast with a clear message if the stream was unreachable or reported an unknown/non-video media type.",
        "The agent called `POST http://localhost:8018/v1/streams/add` with `liveStreamUrl` exactly `rtsp://nv-wowza-pdc.nvidia.com:1935/vod/warehouse_1.mp4` and a description containing `rt-vlm-eval`.",
        "The agent parsed the RT-VLM stream id from the `results[0].id` field returned by `/v1/streams/add`, not from `.streams[0].id`.",
        "The agent called `DELETE http://localhost:8018/v1/streams/delete/<stream_id>` for the temporary `rt-vlm-eval` stream before finishing.",
        "`curl -sf --max-time 15 http://localhost:8018/v1/streams/get-stream-info` returns exit 0 and the response does not contain `rt-vlm-eval`.",
        "The final reply includes a Kafka incident-consumer command using `docker exec` against `mdx-kafka` and `kafka-console-consumer`, with the incident topic derived from the live `KAFKA_INCIDENT_TOPIC` env or the source-backed alerts/profile default `mdx-vlm-incidents`.",
        "The agent did not reference or try to run `tests/kafka/test_kafka_consumer.py`."
      ]
    }
  ]
}