Repository navigation
feat(ai-components): parse agent reply steps from message attachments - #3920
Merged
Merged
Conversation
2 of 6 tasks
isekovanic
force-pushed
the
feat/ai-message-parts
branch
from
November 5, 2026 16:57
f48cdf8 to
b67f35a
Compare
Contributor
SDK Size
|
1 of 6 tasks
isekovanic
added a commit
that referenced
this pull request
Nov 6, 2026
…he agents router (#3921) Ticket: https://linear.app/stream/issue/RN-485 Stacked on #3920. ## 🎯 Goal Groundwork for the agent conversation views: strings that follow the chat's language, and an AI sample that talks to a real agent backend, so the next PRs have reasoning and tool-call steps to show. ## 🛠 Implementation details **Translations** - `useAITranslation()` reads the chat SDK's `TranslationContext`. Inside `<Chat>` it returns the chat's `t`. Without one, it falls back to English with `{{ name }}` placeholders filled. - It's a thin adapter rather than `useTranslationContext()` because ours throws outside a provider, which would crash AI-only apps. - `defaultTranslatorFunction` moved from `Streami18n.ts` to `utils/i18n/utils.ts`, so `TranslationContext.tsx` no longer imports `Streami18n` (i18next and every locale). `Streami18n` still re-exports it, and the public API is unchanged. - `TranslationContext.tsx`, `isTestEnvironment.ts` and `utils/i18n/utils.ts` are on the AI entry's allowlist. The AI entry gains plain `dayjs` and nothing else. - `TranslationProvider` is re-exported from `/ai-components` for apps without `<Chat>`. **ExpoChatGPTSample** - It talks to a Vision-Agents router through `@stream-io/calypso` and no longer uses the old Heroku demo backend. - Each conversation is a router session and its `agent` channel. Questions go through `session.responses.create`, with photos sent as data URIs. Stop goes through `session.interrupt()`. - The drawer lists the user's `agent` channels. A conversation that was never asked anything is deleted when you leave it. - The reply's `ai_*` steps are hidden through the `UnsupportedAttachment` slot until their views land. - Config is read from `.env.local`, and `.env.example` documents it. The README covers running the router. - Hermes has no `crypto.randomUUID`, so the sample polyfills it with stream-chat-js's `generateUUIDv4`. - `<Channel>` and `<MessageList>` are stand-ins until `AIConversation` exists. After that the sample reads the low-level client directly, the same way React's Juno sample does. ## 🎨 UI Changes No SDK UI. The sample now shows real agent replies. ## 🧪 Testing - Unit tests for the translation adapter. They cover English without `<Chat>`, a real `Streami18n` instance (a French string with a placeholder) and the override provider. - On an Android emulator against a local router: - asking a question, the thinking indicator, the stop button showing and the streamed answer; - router-titled conversations, and resuming one; - an unused session being deleted; - no "Unsupported Attachment" cards for the steps. - Not tested: iOS, pressing stop mid-reply, photos, voice mode. - `yarn lint`, `yarn typecheck`, `yarn build` and `yarn test:unit` pass. ## ☑️ Checklist - [x] I have signed the [Stream CLA](https://docs.google.com/forms/d/e/1FAIpQLScFKsKkAJI7mhCr7K9rEIOpqIDThrWxuvxnwUq2XkHyG154vQ/viewform) (required) - [ ] PR targets the `develop` branch (stacked on #3920) - [x] Documentation is updated (sample README) - [ ] New code is tested in main example apps, including all possible scenarios - [ ] SampleApp iOS and Android - [ ] Expo iOS and Android
4 of 6 tasks
isekovanic
added a commit
that referenced
this pull request
Nov 12, 2026
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** - #3920 parse agent reply steps from message attachments - #3921 AI translations through the chat SDK, sample on the agents router - #3924 agent reply steps: reasoning, tool calls, approvals - #3926 native `AIAgent` module for the install id and tool-call sign-in - #3928 message views, reply actions and icon overrides - #3929 `AIConversation` on LegendList - #3931 chat options, suggestions and attachment preview fixes - #3933 client tool runner - #3934 polish of agent conversations - #3936 generated UI with an A2UI renderer - #3944 follow-up polish of agent conversations - #3958 A2UI list-row secrets and malformed messages - #3957 conversation state with `AIConversationController` - #3960 `AIConversation` in its own entry point - #3963 the crew assistant demo app - #3974 alignment with the other SDKs - #3975 StrictMode-safe controller lifecycle and `custom.uiAction` docs - #3976 crew drawer layout - #3978 the samples on `@stream-io/stream-agents` 0.4.2, in place of calypso and their own chat layer 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 use stream-agents' `AgentChat`, whose stream-chat 10 reader reads `channel.messagePaginator`, activates the channel so the client reloads it after a reconnect, and loads older pages with `toTail()`. The samples read the reply fields from `custom`, and 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. They stay on stream-chat `^10.0.1`: stream-agents asks for `^10.0.2`, but only when it builds its own client, and the samples hand it theirs. ## 🎨 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. After the move to stream-agents, both samples were checked again on both platforms: replies, the device time tool, the agent-first Clock in flow, the drawer, reopening from history, handbook sources, and an approval card into A2UI. Reconnect, older pages and voice memos were tested on the samples' previous chat layer, not again since. 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 - [x] I have signed the [Stream CLA](https://docs.google.com/forms/d/e/1FAIpQLScFKsKkAJI7mhCr7K9rEIOpqIDThrWxuvxnwUq2XkHyG154vQ/viewform) (required) - [x] PR targets the `develop` branch - [x] Documentation is updated - [ ] New code is tested in main example apps, including all possible scenarios - [ ] SampleApp iOS and Android - [x] Expo iOS and Android
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
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:
v > 1) keep their payload but have no typed view.approvalandauthorizationare parsed on tool calls.isAwaitingApproval,isAwaitingAuthorization,isAwaitingClient,isDeclined,isToolCallFinished,isAuthorizationExpired,isSupportedPart.One deviation from React: the sign-in URL check doesn't use
URL. On RN < 0.80 itsprotocolandhostgetters throw "not implemented", which would silently drop every sign-in on 0.76–0.79. It's a regex instead.Exported from the
ai-componentsentry only. The main entry is unaffected.🎨 UI Changes
None.
🧪 Testing
messagePartssuite ported to Jest.searchtool call → reasoning).URLand checks a sign-in still parses.yarn lint,yarn test:typecheck,yarn buildandyarn test:unitpass.☑️ Checklist
developbranch