mirror of
https://github.com/BerriAI/litellm.git
synced 2026-08-28 05:25:59 +00:00
0fcaadf11c
Relocates ui/litellm-dashboard/e2e_tests to tests/e2e/ui so all end to end suites live under tests/e2e. The suite stays in TypeScript and becomes a self-contained npm package with its own package.json, lockfile and tsconfig instead of leaning on the dashboard's toolchain; the dashboard drops its @playwright/test dependency, e2e scripts and knip/vitest/tsconfig carve-outs. CI paths follow the move: both CircleCI jobs (main e2e and the SERVER_ROOT_PATH migration smoke) and the test_server_root_path workflow now install and run Playwright from tests/e2e/ui, with the node cache keyed on both lockfiles. classify_changes.sh treats tests/e2e/ui as client so spec edits keep skipping backend jobs. The suite's mock LLM fixture is excluded from the e2e basedpyright zero-error gate in pyrightconfig.json since it belongs to the TS suite, not the typed Python harness.
120 lines
3.2 KiB
Python
120 lines
3.2 KiB
Python
"""
|
|
Mock LLM server for UI e2e tests.
|
|
Responds to OpenAI-format endpoints with canned responses.
|
|
"""
|
|
|
|
import time
|
|
import json
|
|
import uuid
|
|
|
|
import uvicorn
|
|
from fastapi import FastAPI, Request
|
|
from fastapi.middleware.cors import CORSMiddleware
|
|
from fastapi.responses import StreamingResponse
|
|
|
|
|
|
app = FastAPI(title="Mock LLM Server")
|
|
app.add_middleware(
|
|
CORSMiddleware,
|
|
allow_origins=["*"],
|
|
allow_methods=["*"],
|
|
allow_headers=["*"],
|
|
)
|
|
|
|
|
|
@app.get("/health")
|
|
async def health():
|
|
return {"status": "ok"}
|
|
|
|
|
|
@app.get("/v1/models")
|
|
@app.get("/models")
|
|
async def list_models():
|
|
return {
|
|
"object": "list",
|
|
"data": [
|
|
{"id": "fake-gpt-4", "object": "model", "owned_by": "mock"},
|
|
{"id": "fake-claude", "object": "model", "owned_by": "mock"},
|
|
],
|
|
}
|
|
|
|
|
|
@app.post("/v1/chat/completions")
|
|
@app.post("/chat/completions")
|
|
async def chat_completions(request: Request):
|
|
body = await request.json()
|
|
model = body.get("model", "mock-model")
|
|
stream = body.get("stream", False)
|
|
|
|
response_id = f"chatcmpl-{uuid.uuid4().hex[:12]}"
|
|
created = int(time.time())
|
|
|
|
if stream:
|
|
|
|
async def stream_generator():
|
|
chunk = {
|
|
"id": response_id,
|
|
"object": "chat.completion.chunk",
|
|
"created": created,
|
|
"model": model,
|
|
"choices": [
|
|
{
|
|
"index": 0,
|
|
"delta": {
|
|
"role": "assistant",
|
|
"content": "This is a mock response.",
|
|
},
|
|
"finish_reason": None,
|
|
}
|
|
],
|
|
}
|
|
yield f"data: {json.dumps(chunk)}\n\n"
|
|
|
|
done_chunk = {
|
|
"id": response_id,
|
|
"object": "chat.completion.chunk",
|
|
"created": created,
|
|
"model": model,
|
|
"choices": [{"index": 0, "delta": {}, "finish_reason": "stop"}],
|
|
}
|
|
yield f"data: {json.dumps(done_chunk)}\n\n"
|
|
yield "data: [DONE]\n\n"
|
|
|
|
return StreamingResponse(stream_generator(), media_type="text/event-stream")
|
|
|
|
return {
|
|
"id": response_id,
|
|
"object": "chat.completion",
|
|
"created": created,
|
|
"model": model,
|
|
"choices": [
|
|
{
|
|
"index": 0,
|
|
"message": {"role": "assistant", "content": "This is a mock response."},
|
|
"finish_reason": "stop",
|
|
}
|
|
],
|
|
"usage": {"prompt_tokens": 10, "completion_tokens": 8, "total_tokens": 18},
|
|
}
|
|
|
|
|
|
@app.post("/v1/embeddings")
|
|
@app.post("/embeddings")
|
|
async def embeddings(request: Request):
|
|
body = await request.json()
|
|
inputs = body.get("input", [""])
|
|
if isinstance(inputs, str):
|
|
inputs = [inputs]
|
|
return {
|
|
"object": "list",
|
|
"data": [
|
|
{"object": "embedding", "index": i, "embedding": [0.0] * 1536}
|
|
for i in range(len(inputs))
|
|
],
|
|
"model": body.get("model", "mock-embedding"),
|
|
"usage": {"prompt_tokens": 5, "total_tokens": 5},
|
|
}
|
|
|
|
|
|
if __name__ == "__main__":
|
|
uvicorn.run(app, host="127.0.0.1", port=8090)
|