Skip to main content

​
Per-key monitoring

For each API key, the dashboard shows:
  • Current usage: progress toward the token limit configured for that key (for example, 230757 / 1000000).
  • Total tokens: cumulative tokens consumed so far.
  • Usage over time: a date-based chart that highlights when usage spiked or dropped.
Typical workflows:
  • Health check:
    • After onboarding the CLI to a team or project, watch the usage graph to confirm that developers are actually using OpenBug and that the pattern matches expectations.
  • Spike investigation:
    • If you see a sudden spike on a given day, correlate it with known events (incidents, large refactors, new services added to a cluster).
  • Per-environment separation:
    • Use different API keys for dev, staging, and prod; the dashboard then acts as a simple monitoring view per environment.

​
What the dashboard does not show

The dashboard is designed for high-level monitoring, not detailed logging:
  • It does not display raw log content or code.
  • It does not show individual prompts or tool calls.
  • It focuses on aggregate usage and limits so you can keep an eye on how heavily OpenBug is being used.
For deeper operational monitoring of your own systems (for example, your application’s logs, metrics, or traces), continue to rely on your existing observability stack; OpenBug complements that by helping you interpret those logs and fix issues faster.