mirror of
https://github.com/CopilotKit/CopilotKit.git
synced 2026-09-14 16:26:20 +08:00
Jordan Ritter
c414fbad23
Refresh d6 fixtures across the rollout cohort: ag2, built-in-agent,
claude-sdk-{python,typescript}, crewai-crews, google-adk, langgraph-fastapi,
langgraph-typescript, langroid, llamaindex, mastra, ms-agent-{dotnet,python},
pydantic-ai, strands. Companion d4/{langgraph-typescript,mastra,ms-agent-dotnet}
chat.json refreshes. Add the missing ms-agent-python/gen-ui-custom.json
to bring the integration up to the standard pill set.
Also narrow aimock/shared/common.json's generic 'hello' fixture to
'hello world' so it no longer shadows D6 pills whose prompts contain
'hello' as a substring (e.g. langgraph-python headless-simple sends
'Say hello in one short sentence.'). 'hello world' is unused by any
current demo pill, so the fixture remains a manual-typing fallback
without poisoning fixture matching.
This is a mid-rollout snapshot — fixture coverage is uneven across
integrations and rides alongside the conveyance shims landed earlier
in this branch.
89 lines
3.4 KiB
JSON
89 lines
3.4 KiB
JSON
{
|
|
"_meta": {
|
|
"description": "D6 fixtures for ag2 / chat-css",
|
|
"sourceFile": "d5-all.json",
|
|
"created": "2026-05-21"
|
|
},
|
|
"fixtures": [
|
|
{
|
|
"match": {
|
|
"userMessage": "verify the css theme rendering",
|
|
"turnIndex": 0,
|
|
"context": "ag2"
|
|
},
|
|
"response": {
|
|
"content": "The chat is themed with hot pink user bubbles and amber assistant bubbles. CSS variables are scoped to .chat-css-demo-scope so the theme does not leak."
|
|
}
|
|
},
|
|
{
|
|
"match": {
|
|
"userMessage": "switch theme to dark mode",
|
|
"turnIndex": 0,
|
|
"context": "ag2"
|
|
},
|
|
"response": {
|
|
"content": "Done — the change_theme tool was invoked and the page is now in dark mode. Frontend tools were registered via useCopilotAction and the agent dispatched the call client-side."
|
|
}
|
|
},
|
|
{
|
|
"match": {
|
|
"userMessage": "tone:professional",
|
|
"turnIndex": 0,
|
|
"context": "ag2"
|
|
},
|
|
"response": {
|
|
"content": "Greetings. I am operating in professional tone. I will provide measured, formal responses calibrated to your stated preferences and refrain from colloquialisms in my replies."
|
|
}
|
|
},
|
|
{
|
|
"match": {
|
|
"userMessage": "tone:casual",
|
|
"turnIndex": 0,
|
|
"context": "ag2"
|
|
},
|
|
"response": {
|
|
"content": "Hey! Casual mode here — I'll keep things friendly and easygoing. Just shoot me whatever you want to know and I'll riff on it without sounding like a press release."
|
|
}
|
|
},
|
|
{
|
|
"match": {
|
|
"userMessage": "expertise:beginner",
|
|
"turnIndex": 0,
|
|
"context": "ag2"
|
|
},
|
|
"response": {
|
|
"content": "Sure! Think of CopilotKit as a friendly toolkit. It helps you add an AI helper to your app. The helper can answer questions, run small tasks, and show buttons or charts when needed."
|
|
}
|
|
},
|
|
{
|
|
"match": {
|
|
"userMessage": "expertise:expert",
|
|
"turnIndex": 0,
|
|
"context": "ag2"
|
|
},
|
|
"response": {
|
|
"content": "CopilotKit composes a runtime adapter (Express/Hono) over the AG-UI SSE protocol; the React client wires hooks (useFrontendTool, useAgentContext) into a typed agent runner. The architecture front-runs round-trip latency by streaming TEXT_MESSAGE_CHUNK and TOOL_CALL events on the same channel."
|
|
}
|
|
},
|
|
{
|
|
"match": {
|
|
"userMessage": "responseLength:concise",
|
|
"turnIndex": 0,
|
|
"context": "ag2"
|
|
},
|
|
"response": {
|
|
"content": "Agent context is a typed payload sent each turn."
|
|
}
|
|
},
|
|
{
|
|
"match": {
|
|
"userMessage": "responseLength:detailed",
|
|
"turnIndex": 0,
|
|
"context": "ag2"
|
|
},
|
|
"response": {
|
|
"content": "Agent context is a typed payload published from the frontend on every turn through the useAgentContext hook. The payload is forwarded into the agent's runtime context (LangGraph 0.6 introduced the `context` channel as the supported relay for per-run frontend-supplied data; legacy `properties` flowed via `forwardedProps` and did not land in `RunnableConfig`). On the Python side, CopilotKitMiddleware reads the value off the runtime context, then routes it into the system-prompt builder so the model sees the user's tone, expertise, and length preferences before each call. The result is per-turn behavior change without a model swap."
|
|
}
|
|
}
|
|
]
|
|
} |