Real portraits, 3D office scene, and reliable streaming chat#1
Draft
FrameworkOPS wants to merge 1 commit into
Draft
Real portraits, 3D office scene, and reliable streaming chat#1FrameworkOPS wants to merge 1 commit into
FrameworkOPS wants to merge 1 commit into
Conversation
The chat API was streaming SSE that failed silently when ANTHROPIC_API_KEY was missing (or any other server error fired) — the client only saw "Stream failed" and showed a generic message. Switched to the AI SDK's streamText + toTextStreamResponse so the route surfaces real error JSON with a 4xx/5xx status, and the client renders the actual error in the chat bubble. For the characters and office: - Replaced the cartoon SVG agents with real photo portraits (next/image loading stable headshots from randomuser.me) plus animated overlays for thinking/talking states and an active-aura glow. - Rebuilt OfficeFloor as a depth-sorted scene: back wall with night-city window, framed art and ceiling light strips; perspective floor grid; workstation pods scaled by depth with chair, 3D desk (top/front/legs), monitor, keyboard and per-agent accessories; ambient color glows and dust particles. - Removed the unused legacy AgentCharacter component.
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
ANTHROPIC_API_KEY), so the client only saw "Stream failed" and showed a generic message. Switched to the AI SDK'sstreamText+toTextStreamResponse, validated env + payload, and the client now parses the plain text stream and renders the actual error from the server when something goes wrong.next/image(stable URLs fromrandomuser.me), with animated talking / thinking overlays, an active aura glow, a soft shadow, and online status dot.OfficeFlooras a depth-sorted scene: back wall with a framed night-city window, ceiling light strips, framed art and a Framework HQ plaque; perspective floor grid; six workstation pods scaled by depth, each with a chair, a 3D desk (top / front / legs / nameplate), monitor, perspective keyboard, and per-agent accessories (coffee with steam, plant, notebook, papers); ambient color glows and floating dust particles.Test plan
/— six workstations are visibly arranged with depth (back row smaller, front row larger) against a windowed back wall.ANTHROPIC_API_KEYset, sending a message renders⚠️ ANTHROPIC_API_KEY is not set on the server…inside the chat bubble.ANTHROPIC_API_KEYset, sending a message streams a real reply from the agent and the portrait shows the talking indicator while streaming.npm run lintandnpm run buildboth pass clean.Generated by Claude Code