Skip to main content

​
About this page

This page is a high-volume Q&A index built from real product behavior in the backend and frontend codepaths. Use it when users ask operational questions and you need fast, practical answers.

​
Quick high-signal answers

  • API flow: create API key -> call POST /v1/response -> reuse returned session_id for follow-ups.
  • System instructions: set in Dashboard -> Bot -> AI Engine -> Behavior (systemInstructions, max 8000 chars).
  • /v1/response auth: Authorization: Bearer vka_... or x-api-key: vka_....
  • Session memory: reuse session_id for follow-up calls.
  • Plan limits (context/tokens): Free 50/4096, Plus 75/8192, Pro 100/16384, Ultra 150/32768.
  • Plan full matrix (verbs/msg-min/context/max-tokens): Free 5/20/50/4096, Plus 10/40/75/8192, Pro 20/100/100/16384, Ultra 40/unlimited/150/32768.

​
API questions

Create an API key, call POST /v1/response with character + messages, then reuse the returned session_id to keep conversation memory. Use stream: true for SSE on Plus/Pro/Ultra.
Send Authorization: Bearer vka_... or x-api-key: vka_....
Use POST /v1/response with character and messages.
Use Authorization: Bearer vka_... (or x-api-key), send character + messages, and reuse session_id across calls. If omitted on first call, API returns a generated session_id you can keep using.
Use POST /v1/image with character and prompt.
A vanity slug/path/URL (for example /v/my_slug).
Yes, /v1/response supports SSE when stream: true.
Streaming is plan-gated; free tier requests can return upgrade-required errors.
Yes, reuse session_id to continue context.
No, system role is blocked on /v1/response.
Yes, via messages[].content image parts or top-level image_urls.
Up to 4 combined per request.
Yes, request-scoped HTTP tools are supported with validation and limits.
messages: max 60; each message text max 4000 chars; total text max 20000 chars; combined image_urls max 4; session_id max 128 chars; tools max 8 definitions and 2 executed calls per request.
Up to 3 active API keys per account.
Request bodies have size guards; oversized JSON payloads are rejected.

​
Plans and limits questions

Free 5/20/50/4096, Plus 10/40/75/8192, Pro 20/100/100/16384, Ultra 40/unlimited/150/32768 (format: verbs/msg-min/context/max-tokens).
Free: 50 context, 4096 max tokens. Plus: 75, 8192. Pro: 100, 16384. Ultra: 150, 32768.
Plus, Pro, and Ultra support stream: true. Free does not.
Free 5, Plus 10, Pro 20, Ultra 40.

​
Discord questions

Most often missing intents, wrong routing mode, or command/channel permission issues.
Use /activate-channel there.
Use /remove-channel.
Default behavior ignores bot-authored messages.
Server reset requires elevated permissions.
Yes, DM reset is user-scoped.
Image generation may be disabled, prompt invalid, or provider temporarily unavailable.
Usually command timeout or permission/runtime failure.
Yes, via command toggles in Discord module settings.
Yes, status type/text/presence are configurable.
Use the server list in Discord module and leave server action.
Multi-bot mention handling intentionally limits responding bots for stability.

​
Memory, knowledge, and training questions

System instructions are persistent behavior rules for the verb. They define response policy and format, while knowledge/memory provide facts and training examples shape style.
Set them in Dashboard -> Bot -> AI Engine -> Behavior (systemInstructions). Max length is 8000 characters.
Up to 50 per verb.
Use knowledge URL scrape to draft title/content/category.
Manually edit the draft entry and tighten structure before saving.
Optional automatic saving of durable facts from conversation history.
Durable facts to keep; explicit exclusions for temporary/noisy details.
Add keywords and ensure examples match real user phrasing.
Yes. Keep one canonical source and remove outdated entries.
Larger context keeps recent flow better but costs more and can add noise.
Yes, entries use importance scoring.
No. Store compact facts and reusable rules.

​
Chat, groups, and realtime questions

Up to 15 owned groups.
Anti-spam filters can block mention floods and invisible-character abuse.
Default 50, capped at 200 per request.
No, private verbs are owner-only.
WebSocket subscriptions broadcast message/typing/update events in real time.
No, owner must transfer ownership or delete the group.
Group owner only.
Yes, chat message image upload path is capped to small file sizes (5MB class limits).

​
Account, billing, and security questions

Up to 3 active keys.
No, revocation is immediate.
Yes. Backup codes are one-time use.
Active paid subscription linkage can block disconnect.
Tier gating: available model set depends on plan.
Credits are exhausted for the account/owner being billed for that request.
Related entities and associations are cleaned up; some owned resources may transfer or be removed.

Bot Settings Reference

Full limits and field behavior for dashboard configuration.

Troubleshooting

Operational fix guide for the most common failures.