Model Healthcheck

# Model Healthcheck Skill

When the user requests a model test, follow these steps:

Steps

1. Get all model list
2. Use `gateway config.get` to read the current config and extract all `provider/model` combinations from `models.providers`.

1. Test all models concurrently
2. For each model, use `sessions_spawn` to run a test:
3. - task: "Reply with exactly: model ok. Only reply these two words."
4. - model: the corresponding provider/model-id
5. - runTimeoutSeconds: 30
6. - cleanup: "delete"

Fire all tests concurrently (multiple `sessions_spawn` calls at once), do not test sequentially.

1. Collect results and summarize
2. Wait for all tests to complete, then summarize as a list:

• provider/model-id — ✅ OK / ❌ Failed (Xs) — error message if any

Fields: - Status: normal reply = ✅, timeout or error = ❌ - Duration: time from spawn to result - Error: if failed, show the specific error (API error, timeout, auth failure, etc.)

1. Output results
2. Send the summary to the user, with a final tally:
3. - Total models tested: X
4. - Passed: X
5. - Failed: X (list failed model names and reasons)

Notes

• Skip the model currently in use (no need to test yourself)
• If the user specifies a particular model, only test that one
• Feishu/WhatsApp and similar platforms don't support markdown tables — use list format instead