Using the chat
The slide-in chat panel — live streaming of reasoning and tool calls, conversation history, the model badge, the approval flow, and the reliability details behind long chats.
The assistant lives in a slide-in global side panel, toggled by the AI Assistant button (a Sparkles icon) in the top-right of the admin header (apps/web/src/components/layout/app-layout.tsx:74-86). The panel UI is built on Airwave's base-lyra AI Elements components (apps/web/src/components/ai-elements/ — conversation, message, prompt-input, reasoning, response, tool).
Streaming
The client uses the AI SDK useChat hook with DefaultChatTransport against /api/ai/chat (ai-chat-panel.tsx:168-177). The server streams a UI-message response via streamText(...).toUIMessageStreamResponse(...) (chat.ts:153-170). You see reasoning, tool calls, tool results, and the final answer appear live. A turn may chain up to 40 steps (stepCountIs(40)) so a long discover → preview → build sequence completes in one turn.
History
Conversations persist to AiConversation / AiMessage (Prisma models in ai.prisma:102-130), keyed per user. New chat and History controls let you start fresh or resume a past thread (ai-chat-panel.tsx:104-140); the history list is fetched via the ai.conversations tRPC query. Each message stores the full AI SDK part list as JSON so a thread replays faithfully — reasoning, tool calls, and results all come back exactly as they happened.
Model badge
A footer badge shows the active model and lets you switch the chat's active connection inline (ModelBadge, ai-chat-panel.tsx:291-319) — handy for moving a heavy build session onto a cheaper or a stronger model without leaving the chat.
The Approve / Deny flow
When the assistant wants to write, the tool card renders an "Apply this change?" footer with Approve / Deny (ai-chat-panel.tsx:242-254). Approving resumes the turn and runs the tool; denying leaves nothing changed. Every write tool flows through this gate — reads never do.
Implementation note: the client sets
sendAutomaticallyWhen: lastAssistantMessageIsCompleteWithApprovalResponsesso the decision actually POSTs the resume request rather than sticking on "Working" (ai-chat-panel.tsx:172-177).
Reliability details
Long AI chats are fragile in specific ways, and the server handles them so a big build session doesn't fall apart:
- Prompt caching. A cache breakpoint is set on the last message so Anthropic reuses the whole prior prefix each turn — a channel-building chat grows past 100k tokens fast (previews are large), and without caching every turn would re-ship all of it (
chat.ts:143-151). Namespaced to Anthropic; a no-op for other providers. - Idle timeout. Bun's default 10s idle timeout is raised to 255s so a slow thinking / tool turn isn't killed mid-stream (
apps/server/src/index.ts:263-271). - Resume / heal. On each request the server strips unsigned / broken reasoning parts while keeping valid signed ones (
stripReasoning,chat.ts:56-63) and injects synthetic "not applied" results for dangling write tool calls you've already moved past (healDanglingToolCalls,chat.ts:79-98) — without this a crashed approval turn would brick the whole conversation.
See also: Building channels & packages · Exploring your library · Connections & keys
Building channels & packages
The assistant's write tools — creating, editing, renumbering, and grouping channels and packages — each pausing for your approval, plus the one-click undo.
Assistant vs the lineup builder
Airwave has two distinct AI systems — the in-the-loop chat and the autonomous durable lineup builder. How they differ, and what they share.