NetXMS Support Forum

Try escaping $ in the query

Hi,

I'm trying to monitor the power consumption on Aruba 6300 switch stacks.  I want to create DCIs for each PSU so I'm looking for a way to find all the PSU instances.   So far I have found the table I need at oid .1.3.6.1.4.1.47196.4.1.1.3.11.2.1

The table contains the PSU information for the stack but there are 2 indexes one at .1.3.6.1.4.1.47196.4.1.1.3.11.2.1.1 for the PSU Group and .1.3.6.1.4.1.47196.4.1.1.3.11.2.1.2 for the PSU slot.  W
The oids I need with the power consumption are .1.3.6.1.4.1.47196.4.1.1.3.11.2.1.1.7.x.y where x is the primary index and y is the secondary index.  The names for the instances are at .1.3.6.1.4.1.47196.4.1.1.3.11.2.1.1.3.x.y  Does anyone have a solution for doing the instance discovery for this kind of situation?

The new overview for package deployment jobs in version 6.x and later is generally great.
However, we haven't yet found a way to stop jobs that are in the "Failed" status. The system keeps trying to run them over and over again. How can we delete these jobs? Right-clicking only allows us to hide all jobs.
Does anyone have any ideas?

О как, понял. Да, я ставил крайнюю версию jaspersoft studio - если не ошибаюсь, что-то в духе 7.0+
Переделаю, отпишусь, спасибо!

Hello @all,

i have following code in a template:


<config>
<core>
<ExternalMetric>WindowsADUserGroup.Count(*):powershell -NoProfile -NonInteractive -Command "Write-Host ((Get-ADGroupMember -Identity '$1' -Recursive | Where-Object { $_.objectClass -eq 'user' }).count)"</ExternalMetric>
</core>
</config>

If i run the code directly on a server, there are no errors..

If i run the script via NetXMS DC, i getting the error that "_.objectClass" is not found...

Where is my fault? I didn't get a solution for that... Many thanks for any help...

Greetings
Marco

Hi Filipp,

unfortunately, we cannot confirm that this fix works.
We have been experiencing this behavior since updating the NetXMS Agent from 5.0.8 to 6.1.1. Is there a setting to disable these messages during user logins?

We have also noticed that the system is now detecting more non-essential installed software, which is flooding our alarm browser.  For example:

CapturePicker 10.0.17763.1 was installed
Hello-Setup 10.0.19585.1001 was installed
File Explorer 10.0.17763.1 was installed

Is there perhaps also a way to hide specific notifications?

Thanks for your help 

But this topology issue seems to persist. I'm not sure if it's due to my wrong configuration. Could you please give me some guidance? Thanks a lot!

The model is deployed using vLLM with the configuration --tool-call-parser=hermes. Could you please provide guidance?

Below is a current example:
[root@ai-app-0l apps]# curl http://IP:8001/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer <your_token>" \
-d '{
  "model": "qwen3.6-35b-a3b",
  "messages": [
    {"role": "user", "content": "What's the weather like in Beijing today?"}
  ],
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "get_weather",
        "description": "Get the current weather for the specified city",
        "parameters": {
          "type": "object",
          "properties": {
            "location": {
              "type": "string",
              "description": "City name, e.g., Beijing, Shanghai"
            }
          },
          "required": ["location"]
        }
      }
    }
  ]
}'

Response:

{
  "id": "chatcmpl-a914ca7d228bc903",
  "object": "chat.completion",
  "created": 1779196243,
  "model": "qwen3.6-35b-a3b",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "\n\n<tool_call>\n<function=get_weather>\n<parameter=location>\nBeijing\n</parameter>\n</function>\n</tool_call>",
        "refusal": null,
        "annotations": null,
        "audio": null,
        "function_call": null,
        "tool_calls": [],
        "reasoning": "Here's a thinking process:\n\n1. **Analyze User Input:**\n - User asks: \"What's the weather like in Beijing today?\"\n - Key entity: Beijing\n - Request: Current weather\n\n2. **Identify Available Tools:**\n - I have one tool: 'get_weather'\n - Tool description: Get the current weather for a specified city\n - Parameters: 'location' (string, required) - City name, e.g., Beijing, Shanghai\n\n3. **Map User Input to Tool Parameters:**\n - 'location' should be \"Beijing\"\n\n4. **Execute Tool Call:**\n - Call 'get_weather' with 'location: \"Beijing\"'\n\n5. **Process Tool Response (Simulation/Expectation):**\n - Since I don't have real-time access, I'll simulate the tool call and assume it returns a reasonable weather response. However, in this environment, I will actually make the tool call and let the system handle it. I'll generate the tool call now.\n\n Tool Call:\n```json\n{\n  \"name\": \"get_weather\",\n  \"parameters\": {\n    \"location\": \"Beijing\"\n  }\n}\n```\n\n6. **Formulate Response:**\n After receiving the tool response, I will present the weather information clearly to the user in Chinese.\n - For now, I'll just make the tool call."
      },
      "logprobs": null,
      "finish_reason": "stop",
      "stop_reason": null,
      "token_ids": null
    }
  ],
  "service_tier": null,
  "system_fingerprint": null,
  "usage": {
    "prompt_tokens": 284,
    "total_tokens": 656,
    "completion_tokens": 372,
    "prompt_tokens_details": null
  },
  "prompt_logprobs": null,
  "prompt_token_ids": null,
  "ky_transfer_params": null
}

V6.1.2

Большое спасибо