FrameworksOfficial

json-render 0.22 streams one generative-UI catalog into native Slack and Teams cards

json-render 0.22.0, released November 4, adds `@json-render/chat`. One component catalog can become a Chat SDK card; `streamCard` edits a thread message as elements arrive, while `toCard` validates the final card against component schemas and optional platform limits. The official example previews Slack Block Kit and Teams Adaptive Cards.

Why it matters

Generative UI is moving beyond the web DOM into native collaboration surfaces. Catalogs, state expressions, and validation can now be reused across chat platforms, reducing the need for a separate tool for every table or chart shape while making platform limits and streaming cadence part of the rendering contract.

A closer look

The renderer resolves prop expressions, visible, and repeat against spec.state and validates concrete props per component even in multi-component catalogs. Streaming posts after a usable root appears and updates at Chat SDK's 500 ms interval, then validates the final card. The merged PR also caps repeat expansion with maxElements to prevent exponential nested growth, rejects children on components without slots and empty root cards, and exposes readable CardSpecError issues for model feedback.

Who this is for

Frontend, agent-platform, and collaboration-product teams reusing one generative-UI catalog across web, Slack, Teams, and other Chat SDK surfaces.

Original sources

Revisions & corrections (1)

— The official release and merged implementation provide a dated, reproducible new rendering surface with explicit validation and platform-limit boundaries.

Related events

Frameworks

AG-UI Kotlin 0.5.0 aligns with 1.0 through interrupts, activities, multimodality, and strict state boundaries

AG-UI released Kotlin core, client, and tools 0.5.0 on November 5. The SDK now targets AG-UI 1.0 with REASONING events, interrupt/resume outcomes, ACTIVITY snapshots and deltas, tool errors, and multimodal user messages, while adding browser Wasm and macOS Arm64 targets and tightening event, input, and RFC 6902 state validation.

Frameworks

AI SDK 7.0.163 honors telemetry content controls and preserves Google streamed tool order and signature history

Vercel released AI SDK 7.0.163 on November 5. `recordInputs` and `recordOutputs` now govern content delivered to integrations and the `ai:telemetry` channel, filtering prompts, tool inputs, response text, and raw span results while retaining application results such as usage. The same release preserves the order of text, complete function calls, and thought signatures in streamed Google responses and across replayed history.

Frameworks

AG-UI brings A2UI Express into ADK and defines recovery boundaries for generation errors, cancellation and disconnects

AG-UI released ag-ui-a2ui-toolkit 0.0.6 on November 2 and ag_ui_adk 0.12.0 on November 3. The toolkit feeds structured A2UI generation errors into the next bounded model attempt and adds an optional Express inference format. ADK can opt into Express per run, incrementally compile it into validated activity updates, and clean up model and producer streams across cancellation, HTTP disconnects and backpressure.