[isekovanic]

Ticket: https://linear.app/stream/issue/RN-485

🎯 Goal

First of a stack of PRs that bring agent conversations to ai-components: reasoning, tool calls, approvals, sign-in and the conversation view, as in StreamChatAI, ai-compose and stream-chat-react#3376.

This one adds only the data model. No UI.

🛠 Implementation details

An agent writes each step of its reply as an attachment (ai_reasoning, ai_tool_call). parseMessageParts(message.attachments) turns those into typed parts and skips everything else, such as images and files.

Ported from React #3376 with the same names and behaviour:

• Lenient decoding: missing fields get defaults and wrong types are ignored.
• Unknown kinds and newer versions (v > 1) keep their payload but have no typed view.
• approval and authorization are parsed on tool calls.
• Helpers for the views to come: isAwaitingApproval, isAwaitingAuthorization, isAwaitingClient, isDeclined, isToolCallFinished, isAuthorizationExpired, isSupportedPart.

One deviation from React: the sign-in URL check doesn't use URL. On RN < 0.80 its protocol and host getters throw "not implemented", which would silently drop every sign-in on 0.76–0.79. It's a regex instead.

Exported from the ai-components entry only. The main entry is unaffected.

🎨 UI Changes

None.

🧪 Testing

• React's messageParts suite ported to Jest.
• A fixture taken from a real reply written by a local Vision-Agents router (reasoning → search tool call → reasoning).
• A regression test that fakes the pre-0.80 URL and checks a sign-in still parses.
• yarn lint, yarn test:typecheck, yarn build and yarn test:unit pass.

☑️ Checklist

• I have signed the Stream CLA (required)
• PR targets the develop branch
• Documentation is updated
• New code is tested in main example apps, including all possible scenarios
  • SampleApp iOS and Android
  • Expo iOS and Android

[Stream-SDK-Bot]

SDK Size

title	develop	branch	diff	status
js_bundle_size	2037 KB	2037 KB	0 B	🟢
ai_components_size	163 KB	167 KB	+4751 B	🟡