Skip to content

Assistants

Settings → Assistants (/admin/settings/ai/assistants) configures the two LLM-backed features Capacitor runs on your behalf: the conversational analytics agent and session title/summary generation. Both reuse vendor credentials from AI providers — this page has no API key fields of its own.

Conversational analytics on the Analytics tab. Uses the Eval Runner API key for the selected vendor. On the tenant-wide view the agent also runs live, event-level queries over KurrentDB Flight SQL (requires a licensed KurrentDB ≥26.1).

KeyDefaultDescription
Analytics:Agent:EnabledMaster switch for the agent.
Analytics:Agent:VendorAnthropic, OpenAI, KurrentAI (on plans that allow it), or Cohere.
Analytics:Agent:ModelThe chat model to use for the selected vendor.
Analytics:Agent:MaxRows5000Row cap on read-model query results returned to the agent.
Analytics:Agent:TimeoutSeconds30Per-query timeout.

See Analytics for the user-facing feature this configures.

Lets the server (re)generate session titles via the refresh button next to a title. API keys are reused from the Eval Runner blocks on AI providers (Evals:ServerRunner:*:ApiKey) — no separate key is needed here.

With one vendor keyed, it’s used automatically. With both keyed, pick a provider with SessionTitle:Provider (anthropic, openai, kurrentai, or cohere) — the regenerate button stays hidden until one is selected. Saved changes take effect immediately; no restart required.

Per-vendor model overrides, each with a built-in default:

KeyDefault
SessionTitle:Anthropic:Modelclaude-haiku-4-5
SessionTitle:OpenAI:Modelgpt-5.5-mini
SessionTitle:KurrentAI:Model@cf/meta/llama-3.3-70b-instruct-fp8-fast
SessionTitle:Cohere:Modelcommand-a-03-2025

SessionTitle:RunTimeoutSeconds bounds the per-attempt wall-clock budget: 5–120, default 30.

When enabled, the server periodically generates titles for ended sessions that only have a raw first-message title (e.g. Claude Desktop sessions whose watcher couldn’t reach the title model).

KeyRangeDefaultDescription
SessionTitle:AutoBackfill:EnabledoffMaster switch for the sweep.
SessionTitle:AutoBackfill:IntervalSeconds60–3600300Seconds between sweep ticks.
SessionTitle:AutoBackfill:MinEndedAgeMinutes1–602Only sessions ended at least this long ago are eligible, giving in-flight watcher title work a grace window.
SessionTitle:AutoBackfill:MaxAttempts1–103Max LLM attempts per session before giving up.
SessionTitle:AutoBackfill:BatchSize1–10020Max sessions processed per sweep tick.
  • AI providers — the vendor credentials both features reuse.
  • Analytics — the user-facing Analytics tab the analytics agent powers.