> ## Documentation Index
> Fetch the complete documentation index at: https://docs.budecosystem.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Troubleshooting

> Common dashboard issues and practical fixes

<Note>
  Use this guide when dashboard values appear stale, missing, inconsistent, or difficult to interpret.
</Note>

## Diagnostic Flow

```mermaid theme={null}
graph TD
    A[Issue observed in Dashboard] --> B{Data missing or unexpected?}
    B -->|Missing| C[Check selected time window]
    B -->|Unexpected| D[Cross-check related charts]
    C --> E[Validate data source activity]
    D --> F[Validate baseline and recent changes]
    E --> G[Use drill-down modules]
    F --> G
```

## Common Issues

### Charts show no data

**Possible causes**

* Time window has insufficient recent activity.
* The selected dimension has no current records.
* Data pipeline delay between event ingestion and chart aggregation.

**What to do**

1. Switch to **LAST 30 DAYS** and re-check.
2. Validate the corresponding project/model has active traffic.
3. Re-open after a short interval and confirm if data appears.

### Delta looks incorrect

**Possible causes**

* Comparing a low-volume period against a high-volume baseline.
* A sudden short spike or outage skews percentage changes.

**What to do**

1. Compare the same metric across 7-day and 30-day windows.
2. Pair delta interpretation with absolute totals, not percentages alone.

### Latency up while API calls are flat

**Likely interpretation**

* Efficiency regression, model change impact, or infrastructure contention.

**What to do**

1. Inspect affected projects in Observability.
2. Check recent model/deployment changes.
3. Validate cluster and endpoint health.

### Token output spikes unexpectedly

**Possible causes**

* Prompt changes increasing completion length.
* Upstream workload shift toward long-form tasks.

**What to do**

1. Compare input/output trend behavior by model.
2. Review prompt templates and response limits.
3. Re-check model routing for the affected project.

## Escalation Checklist

Escalate with this context to reduce turnaround time:

* Metric(s) affected
* Selected time window
* First observed timestamp
* Projects/models impacted
* Recent deployment or routing changes

## Preventive Practices

<Check>Run a short daily dashboard review at a fixed time.</Check>
<Check>Maintain weekly baseline snapshots for key metrics.</Check>
<Check>Track post-change metric movement after every significant rollout.</Check>