feat(examples-chat): turn on A2UI envelope streaming via callback handler#262
Merged
Conversation
Async callback handler tracking per-tool_call_id cumulative arguments
from on_chat_model_stream events. Each growth in the cumulative string
dispatches an a2ui-partial custom event carrying {tool_call_id,
args_so_far}; the frontend partial-args-bridge consumes these and feeds
envelopes into the A2UI surface store as they parse.
Attached only when gen_ui_mode='a2ui'. Sidebands the parent LLM's tool_call_chunks for render_a2ui_surface as a2ui-partial custom events. Together with the frontend partial-args bridge (claude/genui-streaming- frontend-bridge) and the envelope-tool refactor (claude/genui-streaming- envelope-tool), this realises the per-component fallback transition wired by PR #252 — surface mounts on first surfaceUpdate, components flip from fallback to real as dataModelUpdates stream in.
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
3 tasks
blove
added a commit
that referenced
this pull request
May 12, 2026
…at_model_stream) (#264) PR #262 originally hooked into on_chat_model_stream, but that method does not exist on AsyncCallbackHandler — the canonical streaming-token callback (fired by ChatOpenAI when streaming=True) is on_llm_new_token, which delivers each token plus an optional ChatGenerationChunk whose message field carries the AIMessageChunk with tool_call_chunks. Result of the bug: the handler was wired but never invoked at runtime, so adispatch_custom_event never fired and the frontend bridge stayed dormant. Live smoke at /embed confirmed: zero a2ui-partial events on the wire across a 622KB / 412-chunk stream. This hotfix: - Renames the override to on_llm_new_token with the canonical signature (token: str, *, chunk, run_id, parent_run_id, tags, **kwargs). - Reads tool_call_chunks from chunk.message (ChatGenerationChunk wraps the AIMessageChunk in its message field). - Gracefully handles chunk=None (legacy LLM path with no chunk object). - Updates tests to wrap AIMessageChunk in ChatGenerationChunk and call the new method name. Adds a 6th test asserting chunk=None is a no-op.
3 tasks
blove
added a commit
that referenced
this pull request
May 12, 2026
…rk (#271) Brings the canonical smoke checklist current with 29 PRs that landed between Phase 7 (#239) and today without checklist updates. Specifically: Updated sections: - chat-debug devtools — replaced bottom-drawer model with floating launcher + status pill + switch (PRs #249, #251) - Control palette — palette v2 (status pill, shadcn-styled panel, PR #244) - Generative UI / A2UI surfaces — single-bubble invariant (PR #255), parent-emits-envelopes architecture (PR #259), wrapped-content + tool_calls coexistence (PR #255), envelope reorder - Server-side wire format — tool_calls preserved on the final AI - Replaced 'Multi-thread' section with 'Sidenav (thread management)' reflecting the permanent semantic <nav> + Active/Archived sections (PR #253) and removing the old palette-toggled drawer model Added sections: - Cmd+K history search — palette open/search/select/close, archived result subtitle, keyboard navigation (PR #253) - Per-row thread actions — kebab menu order per state (active, pinned, archived), rename + pin/unpin + archive/unarchive + delete flows (PRs #258, #260, #267) - Thread titles — first-user-message derivation, idempotent writes, manual rename precedence (PR #242) - Progressive A2UI streaming — per-component fallback transition observable during streaming window (PRs #252, #261, #262, #268, #269) - Inline checkpoint markers — render between messages during multi-step runs (PR #243) - Responsive sidenav — viewport breakpoints, auto-collapse behavior (PR #240) Total: ~58 new check items across 6 new sections, plus rewrites to 5 existing sections. Original 333-line checklist → 391 lines / 237 check items.
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
1 participant
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.
Summary
Final piece of the progressive A2UI streaming work. The
A2uiPartialHandlerasync callback handler is attached to thegeneratenode whengen_ui_mode='a2ui'. As the parent LLM streamstool_call_chunksforrender_a2ui_surface(added by #259), the handler concatenates per-tool_call_idcumulative argument strings and dispatchesa2ui-partialcustom events viaadispatch_custom_event. The frontend bridge (separate PR) consumes these and feeds the A2UI surface store envelope-by-envelope.Result: the per-component fallback transition wired by #252 is now actually visible. Surface mounts on the first
surfaceUpdate; components show their fallback while theirdataModelUpdateenvelopes stream; each component flips from fallback to real as its binding resolves.Spec:
docs/superpowers/specs/2026-05-12-genui-streaming-sub-llm-design.md.Test plan
pytest tests/test_a2ui_partial_handler.py— 5 testspytest tests/test_streaming_smoke.py— 1 integration test against canned streampytest tests/— 41 tests, all green/embedafter the frontend bridge PR merges: sample DOM via requestAnimationFrame and confirm frames whererender-default-fallbackcount > 0