Overview
Send Helicone alerts about your LLM traffic, such as error rates and cost, to Callgoose SQIBS. Forward the alert to your SQIBS API endpoint and SQIBS opens an incident.
How it works
Want SQIBS to fix known issues before anyone is paged? See Fix known issues automatically.
Step 1: Add the API filter in SQIBS
- In SQIBS, open Services, choose the service that should receive these incidents, and click Add Or Update API Integration.
- Add a filter with these values (there is no built-in Helicone template yet, so enter them by hand):
| Part | Payload JSON key | Key value contains | What it does |
|---|---|---|---|
| Trigger | (none) | No key yet: every message opens an incident. Narrow it after the first test. |
- Choose the Priority for these incidents and click Save.
Not sure of a key? Send one test message first (step below), then build the filter from the real payload.
In the API Integration window, click the round
{} button at the bottom right. Paste a payload that SQIBS received (copy it from the API log). SQIBS lists every key with its value, each with a copy button. Copy the key into Payload JSON key and the value into Key value contains. No need to read the JSON by hand.Step 2: Send Helicone alerts to SQIBS
- In Helicone, open Alerts and create an alert (for example on error rate or cost).
- If the alert offers a webhook destination, enter your SQIBS endpoint:
https://<your-endpoint>/sqibs-api/v1/process?from=helicone&token=<your-token>
Replace <your-endpoint> and <your-token> with the values from your SQIBS account. See how to get the endpoint URL and API tokens.
Helicone's Webhooks settings send every logged request, not alerts; do not point those at SQIBS, or every LLM call would open an incident. 3. Save the alert.
Step 3: Test it
The API log saves payloads only while API Tracking is on for the token. Turn it on under API Tokens before you test; it switches itself off after 48 hours.
- Lower the alert's threshold so it triggers.
- In SQIBS, a new incident opens.
No incident? Open the API log (with API Tracking on). If the payload is there, the filter did not match it: paste it into the JSON key creator and check the keys. If it is not there, check the URL and token in the Helicone alert.
Refine the filter from a real Helicone message
Helicone does not publish a fixed payload, so build the filter from the first message SQIBS receives:
- Turn on API Tracking for the token, send a test from Helicone, and open the API log.
- Paste the payload into the JSON key creator.
- Set the Trigger filter's Payload JSON key to the field that holds the alert state, and Key value contains to the problem value. Use the alert state field; match on the alert id.
- If the payload has a recovery value, add a Resolve filter on the same key with that value.
- In Map incident with, choose an id that stays the same from the problem message to the recovery message (an alert or check id, not a run or event id).
- Set Incident title from to a readable field, such as the alert or check name.
Values in one Key value contains box must all be present. For "critical or warning", add two filters.
Fix known issues automatically
Many alerts have a known fix: restart a service, clear a full disk, run a health check. SQIBS can run that fix for you the moment the incident opens. This is event-driven auto remediation. For example, when Helicone reports a spike in LLM errors from one provider, SQIBS can run a workflow that switches your gateway to the fallback provider.
Safe by design. SQIBS runs only workflows your own engineers wrote and approved for your environment. Nothing is guessed or generated: the same steps an engineer would run by hand, run sooner. If the workflow does not fix the issue, the engineer is paged as usual.
To set it up, in the same API filter:
- Select Workflow: choose the automation workflow to run when this filter opens an incident.
- If success then make incident resolved: turn on to resolve the incident when the workflow succeeds.
- Waiting time for escalate to escalation policies: how many minutes to give the workflow before paging the on-call engineer.
Start with low-risk workflows, such as a health check, and add fixes as you come to trust them.
Learn more:
- Prometheus: incident auto remediation, a full worked example.
- Automation workflow: build a workflow from actions.
- Run workflows where your systems are: SSH, Bash, PowerShell, Python, Ansible, kubectl, Terraform.