Fast triage checklist
- Confirm you are logged into the correct account/workspace.
- Hard refresh the page and retry once.
- Check plan limits (context, tokens, credits, model availability).
- Confirm your verb settings were actually saved.
- Test with a minimal prompt in a clean chat/thread.
Discord issues
Connection failed while linking Discord token
Connection failed while linking Discord token
Verify token format, ensure the token is not already linked to another verb, and retry after a short delay if Discord is rate limiting requests.
The application did not respond
The application did not respond
This usually means command timeout, missing channel permission, or a disabled slash command. Check command toggles and bot permissions in that server/channel.
Bot only responds sometimes
Bot only responds sometimes
In servers, bot response depends on routing: mention, AI channel, or keyword match. If none of those apply, no response is expected.
Bot replies in wrong places or too often
Bot replies in wrong places or too often
Remove AI channels with
/remove-channel and keep mention-only behavior in shared channels./reset fails in server but works in DM
/reset fails in server but works in DM
Server reset requires admin/server-owner/bot-owner level permission. DM reset is user scoped.
Response quality issues
Replies are too short
Replies are too short
Increase max tokens and use a fuller reply style. Also check whether your current plan caps output lower than expected.
Replies are too generic
Replies are too generic
Tighten system instructions, add focused training examples, and lower temperature.
Bot forgets earlier messages
Bot forgets earlier messages
Increase model context (within plan cap) and avoid splitting related topics across many disconnected chats.
Bot misses known docs/knowledge
Bot misses known docs/knowledge
Add or refine knowledge entries, improve titles/categories, and verify entries are active. For URL imports, scrape again and clean the generated draft.
Web search feels noisy or irrelevant
Web search feels noisy or irrelevant
Disable web search for stable topics. Keep it for fresh/live data only.
Performance and timeout issues
Responses are slow
Responses are slow
Reduce context, disable web search, and test a lighter model. Long prompts + web search + high max tokens significantly increase latency.
Intermittent provider failures
Intermittent provider failures
Retries/backoff are built into the call path, but upstream outages still happen. Retry shortly and keep fallback models available in your plan tier.
Image generation fails randomly
Image generation fails randomly
Provider capacity spikes can cause temporary errors. Retry with a shorter prompt and no reference image first.
Account and billing issues
Insufficient credits error
Insufficient credits error
Top up credits or switch to a lower-cost model. Credits are charged to the account tied to the request/verb owner depending on surface.
Model not selectable
Model not selectable
Your plan may not include that model tier. Choose an available model or upgrade.
API key works in dashboard but fails in API calls
API key works in dashboard but fails in API calls
Check header format (
Authorization: Bearer vka_... or x-api-key), key revocation status, and whether you exceeded active key limits.Chat and group issues
Message send blocked
Message send blocked
Anti-spam protections can block mention floods and invisible-character abuse. Remove unusual hidden characters and retry.
Uploads fail
Uploads fail
Ensure the file is an image and under limit for that surface (for chat message uploads, 5MB max).
Group invite problems
Group invite problems
Verify invite code freshness and that owner has not regenerated it recently.
When to contact support
Contact support with:- Exact timestamp (with timezone)
- Verb ID/vanity URL
- Surface (
Discord,chat,API) - Error text + screenshot
- Repro steps from clean session