You need to enable JavaScript to run this app.
Torch Log Service

Torch Log Service

Copy page
Download PDF
No-coding Agent log app
OpenClaw Observability
Copy page
Download PDF
OpenClaw Observability
This section introduces the OpenClaw Observability application for large model monitoring, available in the TLS application marketplace.​
Overview​
By integrating the OpenClaw Observability application, you can observe data and access services such as the OpenClaw Observability dashboard, Trace call chain, and CacheTrace log analysis.​
Monitoring chart details​
The monitoring chart details for the OpenClaw Observability application in TLS are as follows:​
  • OpenClaw Observability dashboard​
  • ​
    Type​
    Chart​
    Overview​
    • Total tokens, total cost, number of conversations, total sessions, message analysis, error messages​
    • Average token consumption per conversation, average cost per conversation​
    • Average token consumption, average cost consumption​
    • Model token consumption distribution, model cost distribution​
    • Provider token consumption distribution, provider cost distribution​
    • Agent token consumption distribution, agent cost distribution​
    • Host token consumption distribution, host cost distribution​
    • Daily tokens, daily cost, daily top 5 host token consumption, daily top 5 host cost​
    • Top 5 tool invocation analysis, queue depth P95, message processing rate​
    Performance analysis​
    • Model invocation latency P95, message processing latency P95,​
    • Blocked session duration P95, blocked session alerts, session state change count​
    • Queue wait latency P95, queue depth P95, throughput per queue lane​
    • Webhook processing latency P95, webhook receive rate, webhook error count​
    Security audit​
    Authentication failure count, connection failure count, pairing change count, access to sensitive data​
    ​
  • Operations observability​
  • ​
    Type​
    Chart​
    Application logs​
    Application log charts (including time, level, subsystem, content)​
    Operations dashboard​
    • Top 5 gateway subsystem Exception logs, gateway log distribution, gateway exit count, gateway configuration change count​
    • gateway Exception overview_Daily, tools execution failure_Daily, websocket error_Daily, configuration error_Daily​
    • gateway Exception distribution, tools execution failure_by cause, websocket error_by cause, configuration error_by cause​
    ​
  • Trace call chain​
  • ​
    Type​
    Chart​
    Trace analysis​
    Trace analysis (data retrieval limit is 50,000 entries)​
    ​
  • CacheTrace analysis​
  • ​
    Chart​
    Note​
    CacheTrace analysis​
    Includes RUN ID, Total Token, start time, end time, and content for CacheTrace analysis​
    ​
  • Topic list​
  • Displays the projects and log topics corresponding to the following log types:​
  • App logs​
  • Configuration logs​
  • Trace logs​
  • Metric​
  • Session logs​
Integrate log applications​
For steps to integrate the OpenClaw Observability log application, see Integrate OpenClaw observation.​
Manage my applications​
After successfully integrating a log application, you can perform the following management operations on the integrated log applications:​
  1. Log in to the TLS console.​
  1. In the top navigation bar, select the region where TLS is located.​
  1. In the left navigation bar, select Common features > Log applications.​
  1. Go to the My applications tab. In the Actions column for the corresponding log application, the following management operations are supported:​
  • ​
    Operation​
    Note​
    Access management​
    Click Access management to enter the Access management tab, where you can modify the name and description of the log application being accessed.​
    Cancel access​
    Click Cancel access, confirm the information in the cancel access dialog, and then click Cancel access again.​
    ​
​
Last updated: 2026.04.24 17:10:49