mirror of https://github.com/CopilotKit/CopilotKit.git synced 2026-09-14 16:26:20 +08:00

Files

T

History

Alem Tuzlak 1ec575ea02 feat(showcase/ag2): port auth, agent-config, voice, multimodal, byoc-hashbrown, byoc-json-render

Adds 6 missing demos to the AG2 integration:

- auth: V2 runtime onRequest hook gates requests via Bearer token; AG2
  default agent backs the authenticated path.
- agent-config: Typed tone/expertise/responseLength config forwarded via
  agent.setState into AG2 ContextVariables; agent reads via a
  get_current_config tool before each reply.
- voice: V2 runtime + TranscriptionServiceOpenAI + sample audio button;
  guarded for missing OPENAI_API_KEY.
- multimodal: Dedicated gpt-4o AG2 ConversableAgent with image + PDF
  attachment support; sample-attachment buttons inject bundled samples.
- byoc-hashbrown: AG2 agent emits hashbrown-shaped JSON for
  @hashbrownai/react useUiKit + useJsonParser; sales dashboard catalog.
- byoc-json-render: AG2 agent emits flat root/elements JSON spec for
  @json-render/react Renderer; identical sales catalog for parity.

Adds @copilotkit/voice, @json-render/core, @json-render/react, openai
JS deps; pypdf and openai Python deps. Bundles demo-audio + demo-files
public assets and updates manifest features + demos.

2026-04-29 11:25:19 +02:00

README.md

feat(showcase/ag2): port auth, agent-config, voice, multimodal, byoc-hashbrown, byoc-json-render

2026-04-29 11:25:19 +02:00

sample.wav

feat(showcase/ag2): port auth, agent-config, voice, multimodal, byoc-hashbrown, byoc-json-render

2026-04-29 11:25:19 +02:00

README.md

Voice demo audio

Drop a small (<100KB) WAV file named sample.wav in this directory. The voice demo (/demos/voice) fetches it client-side and POSTs to the transcription endpoint so the flow works without mic permissions.

Expected content: an audio clip speaking the phrase "What is the weather in Tokyo?" — the demo caption advertises that phrase to the user, and the bundled QA checklist + E2E spec assert the transcribed text contains "weather" and/or "Tokyo".

Generate locally, for example:

macOS: say -o sample.aiff "What is the weather in Tokyo?" && ffmpeg -i sample.aiff -ar 16000 -ac 1 sample.wav
Linux: espeak-ng -w sample.wav "What is the weather in Tokyo?"
Windows: PowerShell System.Speech.Synthesis.SpeechSynthesizer → SetOutputToWaveFile

Target: 16kHz mono, 3-5s duration, <100KB.