11b3bc2bbf00889a2cd8524438afcaea0fa5b285
Deploy Research Workbench / deploy (push) Failing after 14m1s
- bundle/bundle.md: Add provider-anthropic with source URL and orchestrator config override to disable extended_thinking (foundation enables it by default, causes empty text responses for simple queries) - Dockerfile: Add amplifier-module-provider-anthropic pip install for container - backend/agui_adapter.py: Fix thinking block handling and empty text block rendering - Thinking blocks no longer fall through to text handler - Text blocks only emit START when actual content arrives - Handle amplifierd wire format (block_index/block_type, complete text in content_block:end) - frontend/src/hooks/useChat.ts: Reset assistantId on TEXT_MESSAGE_END to prevent stale message IDs across turns - tests/test_agui_adapter.py: Add extended thinking test coverage Chat functionality now works end-to-end. Verified: login -> create session -> send message -> receive AI response visible in chat UI. Generated with Amplifier
Research Workbench
AI-powered research tool: chat + live browser + artifacts. Backed by amplifierd.
See DESIGN.md for the full architecture.
Quick Start
# Build
docker build -t research-workbench .
# Run
docker run -d --name research-workbench \
-p 8080:8080 \
-p 6080:6080 \
-e ANTHROPIC_API_KEY="$ANTHROPIC_API_KEY" \
research-workbench
research.ampbox.io -- the app vnc.ampbox.io -- the live browser
Description
Languages
TypeScript
51.6%
Python
24.2%
Shell
17.8%
HTML
2.7%
CSS
2%
Other
1.7%