[isekovanic]

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

🎯 Goal

Bring the AI agent work we shipped on v9-release to V10: the same components, APIs and sample apps, adapted to stream-chat 10 and the V10 i18n.

The long-press Copy/Edit menu on the person's own messages isn't here. It isn't on v9 either, and it comes later as a V10 feature.

🛠 Implementation details

The branch is one commit per v9 PR, in merge order, then the V10-only changes, so it can be reviewed commit by commit.

Ported from v9

• feat(ai-components): parse agent reply steps from message attachments #3920 parse agent reply steps from message attachments
• feat(ai-components): AI translations via the chat SDK, AI sample on the agents router #3921 AI translations through the chat SDK, sample on the agents router
• feat(ai-components): agent reply steps (reasoning, tool calls, approvals) #3924 agent reply steps: reasoning, tool calls, approvals
• feat(ai-components): native AIAgent module for install id and tool-call sign-in #3926 native AIAgent module for the install id and tool-call sign-in
• feat(ai-components): message views, reply actions and icon overrides #3928 message views, reply actions and icon overrides
• feat(ai-components): AIConversation on LegendList #3929 AIConversation on LegendList
• feat(ai-components): chat options, suggestions and attachment preview fixes #3931 chat options, suggestions and attachment preview fixes
• feat(ai-components): client tool runner #3933 client tool runner
• feat(ai-components): polish agent conversations #3934 polish of agent conversations
• feat(ai-components): generated UI with an A2UI renderer #3936 generated UI with an A2UI renderer
• fix(ai-components): follow-up polishing of agent conversations #3944 follow-up polish of agent conversations
• fix(a2ui): keep list-row secrets private and recover from a malformed message #3958 A2UI list-row secrets and malformed messages
• feat(ai-components): conversation state with AIConversationController #3957 conversation state with AIConversationController
• feat(ai-components): move AIConversation to its own entry point #3960 AIConversation in its own entry point
• feat(ExpoCrewAssistant): restaurant team assistant demo #3963 the crew assistant demo app
• fix(ai-components): align agent conversations with the other SDKs #3974 alignment with the other SDKs
• fix(ai-components): document a StrictMode-safe controller lifecycle and custom.uiAction #3975 StrictMode-safe controller lifecycle and custom.uiAction docs
• fix: improve drawer layout #3976 crew drawer layout

Where develop had already changed the same lines (comment cleanups, the i18n move, a11y docs), develop's version wins.

What's different on V10

• Fields under custom. stream-chat 10 keeps mime_type, file_size, ai_generated, generating, ai_ui and the step fields under custom. parseMessageParts and fromStreamMessage lift them with a small withCustomFields helper, as the React SDK does.
• Translation keys. The 55 AI and A2UI strings use catalog keys with their English inline, named after React's (aiComponents.replyActions.copy.accessibilityLabel, a2ui.modal.close.label, …), and keys.ts is regenerated. useAITranslation returns core's typed t.
• Entry isolation. The AI entry points may reach V10's translation context. @legendapp/list and react-native-keyboard-controller are AI-only packages.
• LegendList stays at 3.7.1, the version v9 resolves. 3.7.2 keeps fewer rows mounted after a jump, so the reused-rows test now only compares rows that stay mounted. It passes on both versions.
• Sample data layer. Both samples read messages straight from channel.messagePaginator, through a small useAgentMessages hook, and load older pages with toTail(). A followed channel is activated, as <Channel> does, so the client reloads it after a reconnect, and the samples have no recovery code of their own. The only event they still listen to is message.updated, which feeds calypso's LiveReasoning. The crew sample uploads voice memos with uploadChannelFile.
• Sample dependencies. Both samples depend on @stream-io/state-store and use-sync-external-store, and pin @stream-io/state-store to one copy in tsconfig paths.

🎨 UI Changes

None compared with v9. The screenshots are in the v9 PRs above.

🧪 Testing

yarn lint, yarn typecheck, test:typecheck, the unit tests and yarn build pass, and both samples typecheck.

On an Android emulator and an iOS simulator:

• ChatGPT sample: reasoning, the device time tool, the generated Lisbon plan, the drawer, reopening a conversation from history, and starters on a new one.
• Crew sample:
  • all eight flows, including the approval cards, the checklist and form actions, and the agent-first ones;
  • the equipment deep link, photo troubleshooting and the team lead view;
  • voice memos, recorded on the simulator with say and answered;
  • the clock-out form on iOS.
• Reconnect: the network was dropped mid-reply on both samples. The client recovered the active channel, and the full reply appeared.
• Older messages: with the page size briefly set to 3, older pages loaded until there were none left.

Not tested here: voice mode (the simulator's speech recognition doesn't hear say), dictation, Cal.com sign-in, and charts or photos in the ChatGPT sample.

☑️ 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	2027 KB	2033 KB	+6261 B	🔴
ai_components_size	163 KB	344 KB	+185900 B	🔴
a2ui_size	n/a	103 KB	n/a	🆕