mirror of
https://github.com/CopilotKit/CopilotKit.git
synced 2026-09-14 16:26:20 +08:00
Benjamin Taylor
2810f36df6
The 6 OpenAI drop-in integration examples enabled for the CLI's keyless AIMock mock mode shipped fixtures that did not cover the prompts each starter's own UI suggests, so a keyless first-run user clicking the demo suggestions mostly hit the generic catch-all. Re-key/extend each example's fixtures/default.json (substring, most-specific-first, catch-all last) so the surfaced suggestions return scripted replies. ENT-1003.
35 lines
1.4 KiB
JSON
35 lines
1.4 KiB
JSON
{
|
|
"fixtures": [
|
|
{
|
|
"match": { "userMessage": "Hello" },
|
|
"response": {
|
|
"content": "Hello! I'm the pydantic-ai AI assistant. How can I help you?"
|
|
}
|
|
},
|
|
{
|
|
"match": { "userMessage": "what can you do" },
|
|
"response": {
|
|
"content": "I can help you manage and discuss proverbs. I can show you the current list, add new proverbs, replace the whole list, or just chat about them. I can also look up the weather for any location, and change the app's theme color on request."
|
|
}
|
|
},
|
|
{
|
|
"match": { "userMessage": "proverb" },
|
|
"response": {
|
|
"content": "Here are the proverbs in your list so far: \"CopilotKit may be new, but it's the best thing since sliced bread.\" Would you like to add more, update the list, or discuss one of them?"
|
|
}
|
|
},
|
|
{
|
|
"match": { "userMessage": "weather" },
|
|
"response": {
|
|
"content": "I can look up the weather for any location! Which city or place would you like to check?"
|
|
}
|
|
},
|
|
{
|
|
"match": {},
|
|
"response": {
|
|
"content": "You're currently running against aimock (a mock LLM server). This response is a catch-all for requests that don't match any test fixture. To use a real LLM: (1) Add your OPENAI_API_KEY to .env, (2) Remove or unset OPENAI_BASE_URL from your environment so requests go to OpenAI instead of aimock, (3) Restart with `pnpm dev`."
|
|
}
|
|
}
|
|
]
|
|
}
|