mirror of
https://github.com/crewAIInc/crewAI.git
synced 2026-01-23 07:08:14 +00:00
test: add async LLM usage test with stop parameter
This commit is contained in:
Greyson LaLonde
@@ -0,0 +1,213 @@
|
||||
interactions:
|
||||
- request:
|
||||
body: '{"messages":[{"role":"user","content":"Tell me a joke."}],"model":"gpt-4o-mini","stop":["END"]}'
|
||||
headers:
|
||||
User-Agent:
|
||||
- X-USER-AGENT-XXX
|
||||
accept:
|
||||
- application/json
|
||||
accept-encoding:
|
||||
- ACCEPT-ENCODING-XXX
|
||||
authorization:
|
||||
- AUTHORIZATION-XXX
|
||||
connection:
|
||||
- keep-alive
|
||||
content-length:
|
||||
- '95'
|
||||
content-type:
|
||||
- application/json
|
||||
host:
|
||||
- api.openai.com
|
||||
x-stainless-arch:
|
||||
- X-STAINLESS-ARCH-XXX
|
||||
x-stainless-async:
|
||||
- async:asyncio
|
||||
x-stainless-lang:
|
||||
- python
|
||||
x-stainless-os:
|
||||
- X-STAINLESS-OS-XXX
|
||||
x-stainless-package-version:
|
||||
- 1.83.0
|
||||
x-stainless-raw-response:
|
||||
- 'true'
|
||||
x-stainless-read-timeout:
|
||||
- X-STAINLESS-READ-TIMEOUT-XXX
|
||||
x-stainless-retry-count:
|
||||
- '0'
|
||||
x-stainless-runtime:
|
||||
- CPython
|
||||
x-stainless-runtime-version:
|
||||
- 3.12.10
|
||||
method: POST
|
||||
uri: https://api.openai.com/v1/chat/completions
|
||||
response:
|
||||
body:
|
||||
string: "{\n \"id\": \"chatcmpl-D12bQ6vMcLYBu6WGhMwQKenus7ejH\",\n \"object\":
|
||||
\"chat.completion\",\n \"created\": 1769140704,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
|
||||
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
|
||||
\"assistant\",\n \"content\": \"Why did the scarecrow win an award?\\n\\nBecause
|
||||
he was outstanding in his field!\",\n \"refusal\": null,\n \"annotations\":
|
||||
[]\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n
|
||||
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 12,\n \"completion_tokens\":
|
||||
17,\n \"total_tokens\": 29,\n \"prompt_tokens_details\": {\n \"cached_tokens\":
|
||||
0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\":
|
||||
{\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
|
||||
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
|
||||
\"default\",\n \"system_fingerprint\": \"fp_29330a9688\"\n}\n"
|
||||
headers:
|
||||
Access-Control-Expose-Headers:
|
||||
- ACCESS-CONTROL-XXX
|
||||
CF-RAY:
|
||||
- CF-RAY-XXX
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Type:
|
||||
- application/json
|
||||
Date:
|
||||
- Fri, 23 Jan 2026 03:58:25 GMT
|
||||
Server:
|
||||
- cloudflare
|
||||
Set-Cookie:
|
||||
- SET-COOKIE-XXX
|
||||
Strict-Transport-Security:
|
||||
- STS-XXX
|
||||
Transfer-Encoding:
|
||||
- chunked
|
||||
X-Content-Type-Options:
|
||||
- X-CONTENT-TYPE-XXX
|
||||
alt-svc:
|
||||
- h3=":443"; ma=86400
|
||||
cf-cache-status:
|
||||
- DYNAMIC
|
||||
content-length:
|
||||
- '886'
|
||||
openai-organization:
|
||||
- OPENAI-ORG-XXX
|
||||
openai-processing-ms:
|
||||
- '519'
|
||||
openai-project:
|
||||
- OPENAI-PROJECT-XXX
|
||||
openai-version:
|
||||
- '2020-10-01'
|
||||
x-envoy-upstream-service-time:
|
||||
- '652'
|
||||
x-openai-proxy-wasm:
|
||||
- v0.1
|
||||
x-ratelimit-limit-requests:
|
||||
- X-RATELIMIT-LIMIT-REQUESTS-XXX
|
||||
x-ratelimit-limit-tokens:
|
||||
- X-RATELIMIT-LIMIT-TOKENS-XXX
|
||||
x-ratelimit-remaining-requests:
|
||||
- X-RATELIMIT-REMAINING-REQUESTS-XXX
|
||||
x-ratelimit-remaining-tokens:
|
||||
- X-RATELIMIT-REMAINING-TOKENS-XXX
|
||||
x-ratelimit-reset-requests:
|
||||
- X-RATELIMIT-RESET-REQUESTS-XXX
|
||||
x-ratelimit-reset-tokens:
|
||||
- X-RATELIMIT-RESET-TOKENS-XXX
|
||||
x-request-id:
|
||||
- X-REQUEST-ID-XXX
|
||||
status:
|
||||
code: 200
|
||||
message: OK
|
||||
- request:
|
||||
body: '{"messages":[{"role":"user","content":"Tell me a joke."}],"model":"gpt-4o-mini","stop":["END"]}'
|
||||
headers:
|
||||
User-Agent:
|
||||
- X-USER-AGENT-XXX
|
||||
accept:
|
||||
- application/json
|
||||
accept-encoding:
|
||||
- ACCEPT-ENCODING-XXX
|
||||
authorization:
|
||||
- AUTHORIZATION-XXX
|
||||
connection:
|
||||
- keep-alive
|
||||
content-length:
|
||||
- '95'
|
||||
content-type:
|
||||
- application/json
|
||||
host:
|
||||
- api.openai.com
|
||||
x-stainless-arch:
|
||||
- X-STAINLESS-ARCH-XXX
|
||||
x-stainless-async:
|
||||
- async:asyncio
|
||||
x-stainless-lang:
|
||||
- python
|
||||
x-stainless-os:
|
||||
- X-STAINLESS-OS-XXX
|
||||
x-stainless-package-version:
|
||||
- 1.83.0
|
||||
x-stainless-raw-response:
|
||||
- 'true'
|
||||
x-stainless-read-timeout:
|
||||
- X-STAINLESS-READ-TIMEOUT-XXX
|
||||
x-stainless-retry-count:
|
||||
- '0'
|
||||
x-stainless-runtime:
|
||||
- CPython
|
||||
x-stainless-runtime-version:
|
||||
- 3.12.10
|
||||
method: POST
|
||||
uri: https://api.openai.com/v1/chat/completions
|
||||
response:
|
||||
body:
|
||||
string: ''
|
||||
headers:
|
||||
Access-Control-Expose-Headers:
|
||||
- ACCESS-CONTROL-XXX
|
||||
CF-RAY:
|
||||
- CF-RAY-XXX
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Type:
|
||||
- application/json
|
||||
Date:
|
||||
- Fri, 23 Jan 2026 03:58:25 GMT
|
||||
Server:
|
||||
- cloudflare
|
||||
Set-Cookie:
|
||||
- SET-COOKIE-XXX
|
||||
Strict-Transport-Security:
|
||||
- STS-XXX
|
||||
Transfer-Encoding:
|
||||
- chunked
|
||||
X-Content-Type-Options:
|
||||
- X-CONTENT-TYPE-XXX
|
||||
alt-svc:
|
||||
- h3=":443"; ma=86400
|
||||
cf-cache-status:
|
||||
- DYNAMIC
|
||||
content-length:
|
||||
- '0'
|
||||
openai-organization:
|
||||
- OPENAI-ORG-XXX
|
||||
openai-processing-ms:
|
||||
- '519'
|
||||
openai-project:
|
||||
- OPENAI-PROJECT-XXX
|
||||
openai-version:
|
||||
- '2020-10-01'
|
||||
x-envoy-upstream-service-time:
|
||||
- '652'
|
||||
x-openai-proxy-wasm:
|
||||
- v0.1
|
||||
x-ratelimit-limit-requests:
|
||||
- X-RATELIMIT-LIMIT-REQUESTS-XXX
|
||||
x-ratelimit-limit-tokens:
|
||||
- X-RATELIMIT-LIMIT-TOKENS-XXX
|
||||
x-ratelimit-remaining-requests:
|
||||
- X-RATELIMIT-REMAINING-REQUESTS-XXX
|
||||
x-ratelimit-remaining-tokens:
|
||||
- X-RATELIMIT-REMAINING-TOKENS-XXX
|
||||
x-ratelimit-reset-requests:
|
||||
- X-RATELIMIT-RESET-REQUESTS-XXX
|
||||
x-ratelimit-reset-tokens:
|
||||
- X-RATELIMIT-RESET-TOKENS-XXX
|
||||
x-request-id:
|
||||
- X-REQUEST-ID-XXX
|
||||
status:
|
||||
code: 200
|
||||
message: OK
|
||||
version: 1
|
||||
@@ -959,6 +959,38 @@ async def test_usage_info_non_streaming_with_acall():
|
||||
assert len(result) > 0
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
@pytest.mark.vcr(record_mode="once",decode_compressed_response=True,match_on=["method", "scheme", "host", "path", "body"])
|
||||
async def test_usage_info_non_streaming_with_acall_and_stop():
|
||||
llm = LLM(
|
||||
model="openai/gpt-4o-mini",
|
||||
is_litellm=True,
|
||||
stream=False,
|
||||
stop=["END"],
|
||||
)
|
||||
|
||||
assert llm._token_usage == {
|
||||
"total_tokens": 0,
|
||||
"prompt_tokens": 0,
|
||||
"completion_tokens": 0,
|
||||
"successful_requests": 0,
|
||||
"cached_prompt_tokens": 0,
|
||||
}
|
||||
|
||||
with patch.object(
|
||||
llm, "_ahandle_non_streaming_response", wraps=llm._ahandle_non_streaming_response
|
||||
) as mock_handle:
|
||||
result = await llm.acall("Tell me a joke.")
|
||||
mock_handle.assert_called_once()
|
||||
|
||||
assert llm._token_usage["successful_requests"] == 1
|
||||
assert llm._token_usage["prompt_tokens"] > 0
|
||||
assert llm._token_usage["completion_tokens"] > 0
|
||||
assert llm._token_usage["total_tokens"] > 0
|
||||
|
||||
assert len(result) > 0
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
@pytest.mark.vcr(record_mode="none",decode_compressed_response=True,match_on=["method", "scheme", "host", "path", "body"])
|
||||
async def test_usage_info_streaming_with_acall():
|
||||
|
||||
Reference in New Issue
Block a user