andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-09-11 05:39:39 +00:00
Code Issues Actions 8 Packages Projects Releases Wiki Activity

Merge branch 'main' into fix/native-tool-call-responses-api-shape

Browse Source
This commit is contained in:
Rip&Tear
2026-08-08 00:16:26 +08:00
committed by GitHub
parent ed727230e0 e264e058a7
commit 05f9ef91d7
33 changed files with 556 additions and 227 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
lib/crewai/src/crewai/llm.py
View File

@@ -2225,14 +2225,14 @@ class LLM(BaseLLM):
)
return messages
provider = self.provider or self.model
formatter = self._multimodal_formatter_name()
for msg in messages:
files = msg.get("files")
if not files:
continue
content_blocks = format_multimodal_content(files, provider)
content_blocks = format_multimodal_content(files, formatter)
if not content_blocks:
msg.pop("files", None)
continue
@@ -2250,6 +2250,13 @@ class LLM(BaseLLM):
return messages
def _multimodal_formatter_name(self) -> str:
# Identity (`self.provider`) stays e.g. anthropic. LiteLLM's completion()
# API is OpenAI-shaped and translates blocks to the vendor on the wire.
if self.is_litellm:
return "openai"
return self.provider or self.model
async def _aprocess_message_files(
self, messages: list[LLMMessage]
) -> list[LLMMessage]:
@@ -2276,14 +2283,14 @@ class LLM(BaseLLM):
)
return messages
provider = self.provider or self.model
formatter = self._multimodal_formatter_name()
for msg in messages:
files = msg.get("files")
if not files:
continue
content_blocks = await aformat_multimodal_content(files, provider)
content_blocks = await aformat_multimodal_content(files, formatter)
if not content_blocks:
msg.pop("files", None)
continue

13
lib/crewai/src/crewai/llms/base_llm.py
View File

@@ -274,7 +274,10 @@ class BaseLLM(BaseModel, ABC):
data["stop"] = list(stop)
if not data.get("provider"):
data["provider"] = "openai"
model = data.get("model") or ""
data["provider"] = (
cls._extract_provider(model) if isinstance(model, str) else "openai"
)
known_fields = set(cls.model_fields.keys())
extras = {k: v for k, v in data.items() if k not in known_fields}
@@ -507,6 +510,10 @@ class BaseLLM(BaseModel, ABC):
"""
return False
def _multimodal_formatter_name(self) -> str:
# Content-block schema key for crewai_files. Identity stays on self.provider.
return self.provider or self.model
def format_text_content(self, text: str) -> dict[str, Any]:
"""Format text as a content block for the LLM.
@@ -866,7 +873,7 @@ class BaseLLM(BaseModel, ABC):
)
return messages
provider = getattr(self, "provider", None) or getattr(self, "model", "openai")
formatter = self._multimodal_formatter_name()
api = getattr(self, "api", None)
for msg in messages:
@@ -878,7 +885,7 @@ class BaseLLM(BaseModel, ABC):
text = existing_content if isinstance(existing_content, str) else None
content_blocks = format_multimodal_content(
files, provider, api=api, prefer_upload=self.prefer_upload, text=text
files, formatter, api=api, prefer_upload=self.prefer_upload, text=text
)
if not content_blocks:
msg.pop("files", None)

14
lib/crewai/src/crewai/llms/providers/anthropic/completion.py
View File

@@ -12,6 +12,7 @@ from crewai.llms.base_llm import BaseLLM, JsonResponseFormat, llm_call_context
from crewai.llms.hooks.base import BaseInterceptor
from crewai.llms.hooks.transport import AsyncHTTPTransport, HTTPTransport
from crewai.llms.providers.utils.common import safe_tool_conversion
from crewai.types.usage_metrics import _coerce_int
from crewai.utilities.agent_utils import is_context_length_exceeded
from crewai.utilities.exceptions.context_window_exceeding_exception import (
LLMContextLengthExceededError,
@@ -1965,12 +1966,15 @@ class AnthropicCompletion(BaseLLM):
"""Extract token usage and response metadata from Anthropic response."""
if hasattr(response, "usage") and response.usage:
usage = response.usage
input_tokens = getattr(usage, "input_tokens", 0)
output_tokens = getattr(usage, "output_tokens", 0)
cache_read_tokens = getattr(usage, "cache_read_input_tokens", 0) or 0
cache_creation_tokens = (
getattr(usage, "cache_creation_input_tokens", 0) or 0
input_tokens = _coerce_int(getattr(usage, "input_tokens", 0))
output_tokens = _coerce_int(getattr(usage, "output_tokens", 0))
cache_read_tokens = _coerce_int(
getattr(usage, "cache_read_input_tokens", 0)
)
cache_creation_tokens = _coerce_int(
getattr(usage, "cache_creation_input_tokens", 0)
)
input_tokens = input_tokens + cache_read_tokens + cache_creation_tokens
result: dict[str, Any] = {
"input_tokens": input_tokens,
"output_tokens": output_tokens,

41
lib/crewai/src/crewai/types/usage_metrics.py
View File

@@ -108,6 +108,37 @@ class UsageMetrics(BaseModel):
),
)
@staticmethod
def _has_unreconciled_anthropic_cache_keys(usage_data: dict[str, Any]) -> bool:
"""Detect raw Anthropic usage that still splits cache from ``input_tokens``.
The native ``AnthropicCompletion`` provider folds cache read/creation
counters into ``input_tokens`` before usage reaches this normalizer.
LiteLLM and flow-level event aggregation can still deliver the raw
Anthropic API shape, where ``input_tokens`` is only the uncached
portion and cache counters arrive as separate keys. Without
reconciling here, ``prompt_tokens`` and ``total_tokens`` undercount
billed usage on cached Anthropic workloads.
"""
return "input_tokens" in usage_data and (
"cache_read_input_tokens" in usage_data
or "cache_creation_input_tokens" in usage_data
)
@staticmethod
def _resolve_billed_prompt_tokens(usage_data: dict[str, Any]) -> int:
"""Return the full billed prompt/input token count for a usage dict."""
if UsageMetrics._has_unreconciled_anthropic_cache_keys(usage_data):
return (
_coerce_int(usage_data.get("input_tokens"))
+ _coerce_int(usage_data.get("cache_read_input_tokens"))
+ _coerce_int(usage_data.get("cache_creation_input_tokens"))
)
return _first_int(
usage_data, "prompt_tokens", "prompt_token_count", "input_tokens"
)
@classmethod
def from_provider_dict(cls, usage_data: dict[str, Any] | None) -> Self | None:
"""Normalize a provider's raw usage dict into a ``UsageMetrics``.
@@ -125,9 +156,7 @@ class UsageMetrics(BaseModel):
if not usage_data:
return None
prompt_tokens = _first_int(
usage_data, "prompt_tokens", "prompt_token_count", "input_tokens"
)
prompt_tokens = cls._resolve_billed_prompt_tokens(usage_data)
completion_tokens = _first_int(
usage_data,
"completion_tokens",
@@ -145,12 +174,16 @@ class UsageMetrics(BaseModel):
if isinstance(details, dict):
cached_prompt_tokens = _coerce_int(details.get("cached_tokens"))
cache_creation_tokens = _coerce_int(
usage_data.get("cache_creation_tokens")
) or _coerce_int(usage_data.get("cache_creation_input_tokens"))
return cls(
total_tokens=prompt_tokens + completion_tokens,
prompt_tokens=prompt_tokens,
completion_tokens=completion_tokens,
cached_prompt_tokens=cached_prompt_tokens,
reasoning_tokens=_coerce_int(usage_data.get("reasoning_tokens")),
cache_creation_tokens=_coerce_int(usage_data.get("cache_creation_tokens")),
cache_creation_tokens=cache_creation_tokens,
successful_requests=1,
)

7
lib/crewai/src/crewai/utilities/internal_instructor.py
View File

@@ -105,7 +105,12 @@ class InternalInstructor(Generic[T]):
if value is not None:
extra_kwargs[attr] = value
return instructor.from_provider(f"{provider}/{model_string}", **extra_kwargs)
qualified_model = (
model_string
if not provider or model_string.startswith(f"{provider}/")
else f"{provider}/{model_string}"
)
return instructor.from_provider(qualified_model, **extra_kwargs)
def _extract_provider(self) -> str:
"""Extract provider from LLM model name.

105
lib/crewai/tests/cassettes/utilities/test_llm_emits_call_failed_event.yaml
View File

@@ -1,105 +0,0 @@
interactions:
- request:
body: '{"messages": [{"role": "user", "content": "Hello, how are you?"}], "model":
"gpt-4o-mini", "stop": []}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '102'
content-type:
- application/json
cookie:
- _cfuvid=IY8ppO70AMHr2skDSUsGh71zqHHdCQCZ3OvkPi26NBc-1740424913267-0.0.1.1-604800000;
__cf_bm=fU6K5KZoDmgcEuF8_yWAYKUO5fKHh6q5.wDPnna393g-1740424913-1.0.1.1-2iOaq3JVGWs439V0HxJee0IC9HdJm7dPkeJorD.AGw0YwkngRPM8rrTzn_7ht1BkbOauEezj.wPKcBz18gIYUg
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.61.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.61.0
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.8
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: "{\n \"id\": \"chatcmpl-B4YLA2SrC2rwdVQ3U87G5a0P5lsLw\",\n \"object\"\
: \"chat.completion\",\n \"created\": 1740425016,\n \"model\": \"gpt-4o-mini-2024-07-18\"\
,\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \
\ \"role\": \"assistant\",\n \"content\": \"Hello! I'm just a\
\ computer program, so I don't have feelings, but I'm here and ready to help\
\ you. How can I assist you today?\",\n \"refusal\": null\n },\n\
\ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n\
\ \"usage\": {\n \"prompt_tokens\": 13,\n \"completion_tokens\": 30,\n\
\ \"total_tokens\": 43,\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_709714d124\"\n}\n"
headers:
CF-RAY:
- 9171d4c0ed44236e-SJC
Connection:
- keep-alive
Content-Type:
- application/json
Date:
- Mon, 24 Feb 2025 19:23:38 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '1954'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '30000'
x-ratelimit-limit-tokens:
- '150000000'
x-ratelimit-remaining-requests:
- '29999'
x-ratelimit-remaining-tokens:
- '149999978'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_ea2703502b8827e4297cd2a7bae9d9c8
status:
code: 200
message: OK
version: 1

4
lib/crewai/tests/events/test_llm_finish_reason_response_id.py
View File

@@ -4,7 +4,7 @@ from unittest.mock import MagicMock, patch
import pytest
from crewai.events.event_bus import CrewAIEventsBus
from crewai.events.event_bus import crewai_event_bus
from crewai.events.types.llm_events import (
LLMCallCompletedEvent,
LLMCallStartedEvent,
@@ -31,7 +31,7 @@ class _StubLLM(BaseLLM):
@pytest.fixture
def mock_emit():
with patch.object(CrewAIEventsBus, "emit") as mock:
with patch.object(crewai_event_bus, "emit") as mock:
yield mock

130
lib/crewai/tests/events/test_llm_usage_event.py
View File

@@ -4,7 +4,6 @@ from unittest.mock import patch
import pytest
from pydantic import BaseModel
from crewai.events.event_bus import CrewAIEventsBus
from crewai.events.types.llm_events import LLMCallCompletedEvent, LLMCallType
from crewai.llm import LLM
from crewai.llms.base_llm import BaseLLM
@@ -203,7 +202,9 @@ class _StubLLM(BaseLLM):
class TestEmitCallCompletedEventPassesUsage:
@pytest.fixture
def mock_emit(self):
with patch.object(CrewAIEventsBus, "emit") as mock:
from crewai.events.event_bus import crewai_event_bus
with patch.object(crewai_event_bus, "emit") as mock:
yield mock
@pytest.fixture
@@ -297,3 +298,128 @@ class TestUsageMetricsNewFields:
dumped = metrics.model_dump()
assert dumped["reasoning_tokens"] == 10
assert dumped["cache_creation_tokens"] == 5
class TestFromProviderDictAnthropicCacheTokens:
def test_cache_read_tokens_included_in_prompt_and_total(self):
from crewai.types.usage_metrics import UsageMetrics
metrics = UsageMetrics.from_provider_dict(
{
"input_tokens": 3,
"output_tokens": 44,
"cache_read_input_tokens": 2061,
}
)
assert metrics is not None
assert metrics.prompt_tokens == 2064
assert metrics.completion_tokens == 44
assert metrics.total_tokens == 2108
assert metrics.cached_prompt_tokens == 2061
def test_cache_creation_tokens_included_in_prompt_and_total(self):
from crewai.types.usage_metrics import UsageMetrics
metrics = UsageMetrics.from_provider_dict(
{
"input_tokens": 100,
"output_tokens": 50,
"cache_creation_input_tokens": 20,
}
)
assert metrics is not None
assert metrics.prompt_tokens == 120
assert metrics.total_tokens == 170
assert metrics.cache_creation_tokens == 20
def test_cache_read_and_creation_tokens_both_included(self):
from crewai.types.usage_metrics import UsageMetrics
metrics = UsageMetrics.from_provider_dict(
{
"input_tokens": 100,
"output_tokens": 50,
"cache_read_input_tokens": 30,
"cache_creation_input_tokens": 20,
}
)
assert metrics is not None
assert metrics.prompt_tokens == 150
assert metrics.total_tokens == 200
assert metrics.cached_prompt_tokens == 30
assert metrics.cache_creation_tokens == 20
def test_missing_cache_fields_preserve_non_cached_totals(self):
from crewai.types.usage_metrics import UsageMetrics
metrics = UsageMetrics.from_provider_dict(
{"input_tokens": 100, "output_tokens": 50}
)
assert metrics is not None
assert metrics.prompt_tokens == 100
assert metrics.total_tokens == 150
assert metrics.cached_prompt_tokens == 0
assert metrics.cache_creation_tokens == 0
def test_reconciled_native_dict_is_not_double_counted(self):
from crewai.types.usage_metrics import UsageMetrics
metrics = UsageMetrics.from_provider_dict(
{
"input_tokens": 150,
"output_tokens": 50,
"cached_prompt_tokens": 30,
"cache_creation_tokens": 20,
}
)
assert metrics is not None
assert metrics.prompt_tokens == 150
assert metrics.total_tokens == 200
assert metrics.cache_creation_tokens == 20
def test_openai_cached_prompt_tokens_are_not_added_twice(self):
from crewai.types.usage_metrics import UsageMetrics
metrics = UsageMetrics.from_provider_dict(
{
"prompt_tokens": 100,
"completion_tokens": 50,
"prompt_tokens_details": {"cached_tokens": 30},
}
)
assert metrics is not None
assert metrics.prompt_tokens == 100
assert metrics.total_tokens == 150
assert metrics.cached_prompt_tokens == 30
def test_cumulative_usage_via_add_usage_metrics(self):
from crewai.types.usage_metrics import UsageMetrics
first = UsageMetrics.from_provider_dict(
{
"input_tokens": 100,
"output_tokens": 50,
"cache_read_input_tokens": 30,
}
)
second = UsageMetrics.from_provider_dict(
{
"input_tokens": 40,
"output_tokens": 20,
}
)
assert first is not None and second is not None
first.add_usage_metrics(second)
assert first.prompt_tokens == 170
assert first.completion_tokens == 70
assert first.total_tokens == 240
assert first.cached_prompt_tokens == 30
assert first.successful_requests == 2

11
lib/crewai/tests/llms/anthropic/test_anthropic.py
View File

@@ -549,7 +549,12 @@ def test_anthropic_token_usage_tracking():
with patch.object(llm._client.messages, 'create') as mock_create:
mock_response = MagicMock()
mock_response.content = [MagicMock(text="test response")]
mock_response.usage = MagicMock(input_tokens=50, output_tokens=25)
mock_response.usage = MagicMock(
input_tokens=50,
output_tokens=25,
cache_read_input_tokens=0,
cache_creation_input_tokens=0,
)
mock_create.return_value = mock_response
result = llm.call("Hello")
@@ -1653,9 +1658,9 @@ def test_anthropic_cache_creation_tokens_extraction():
mock_response.model = None
usage = llm._extract_anthropic_token_usage(mock_response)
assert usage["input_tokens"] == 100
assert usage["input_tokens"] == 150
assert usage["output_tokens"] == 50
assert usage["total_tokens"] == 150
assert usage["total_tokens"] == 200
assert usage["cached_prompt_tokens"] == 30
assert usage["cache_creation_tokens"] == 20

4
lib/crewai/tests/llms/google/test_google.py
View File

@@ -123,12 +123,12 @@ def test_gemini_completion_initialization_parameters():
def test_gemini_started_event_surfaces_max_output_tokens():
from crewai.events.event_bus import CrewAIEventsBus
from crewai.events.event_bus import crewai_event_bus
from crewai.events.types.llm_events import LLMCallStartedEvent
llm = LLM(model="google/gemini-2.0-flash-001", max_output_tokens=2000, api_key="test-key")
with patch.object(CrewAIEventsBus, "emit") as mock_emit:
with patch.object(crewai_event_bus, "emit") as mock_emit:
llm._emit_call_started_event(messages="hi")
event = mock_emit.call_args[1]["event"]

4
lib/crewai/tests/llms/test_multimodal_integration.py
View File

@@ -77,8 +77,8 @@ startxref
def _build_multimodal_message(llm: LLM, prompt: str, files: dict) -> list[dict]:
"""Build a multimodal message with text and file content."""
provider = getattr(llm, "provider", None) or llm.model
content_blocks = format_multimodal_content(files, provider)
formatter = llm._multimodal_formatter_name()
content_blocks = format_multimodal_content(files, formatter)
return [
{
"role": "user",

14
lib/crewai/tests/llms/test_tool_call_streaming.py
View File

@@ -38,18 +38,10 @@ def get_temperature_tool_schema() -> dict[str, Any]:
@pytest.fixture
def mock_emit() -> MagicMock:
"""Mock the singleton event bus emit used by LLM providers.
from crewai.events.event_bus import crewai_event_bus
Patch the singleton instance (not only the class) so a leftover
instance-level ``emit`` from other tests cannot shadow the mock.
"""
from crewai.events.event_bus import CrewAIEventsBus, crewai_event_bus
with (
patch.object(CrewAIEventsBus, "emit") as class_mock,
patch.object(crewai_event_bus, "emit", new=class_mock),
):
yield class_mock
with patch.object(crewai_event_bus, "emit") as mock:
yield mock
def _event_from_emit_call(call: Any) -> Any:

34
lib/crewai/tests/test_llm.py
View File

@@ -534,9 +534,9 @@ def assert_event_count(
@pytest.fixture
def mock_emit() -> MagicMock:
from crewai.events.event_bus import CrewAIEventsBus
from crewai.events.event_bus import crewai_event_bus
with patch.object(CrewAIEventsBus, "emit") as mock_emit:
with patch.object(crewai_event_bus, "emit") as mock_emit:
yield mock_emit
@@ -860,16 +860,19 @@ def test_prefixed_models_with_invalid_constants_use_litellm():
llm = LLM(model="openai/gemini-2.5-flash", is_litellm=False)
assert llm.is_litellm is True
assert llm.model == "openai/gemini-2.5-flash"
assert llm.provider == "openai"
# Test openai/ prefix with model that doesn't match patterns (e.g. no gpt- prefix) → LiteLLM
llm2 = LLM(model="openai/custom-finetune-model", is_litellm=False)
assert llm2.is_litellm is True
assert llm2.model == "openai/custom-finetune-model"
assert llm2.provider == "openai"
# Test anthropic/ prefix with non-Anthropic model → LiteLLM
llm3 = LLM(model="anthropic/gpt-4o", is_litellm=False)
assert llm3.is_litellm is True
assert llm3.model == "anthropic/gpt-4o"
assert llm3.provider == "anthropic"
def test_prefixed_models_with_valid_patterns_use_native_sdk():
@@ -893,11 +896,38 @@ def test_prefixed_models_with_non_native_providers_use_litellm():
llm = LLM(model="groq/llama-3.3-70b", is_litellm=False)
assert llm.is_litellm is True
assert llm.model == "groq/llama-3.3-70b"
assert llm.provider == "groq"
# Test together/ prefix (not a native provider) → LiteLLM
llm2 = LLM(model="together/qwen-2.5-72b", is_litellm=False)
assert llm2.is_litellm is True
assert llm2.model == "together/qwen-2.5-72b"
assert llm2.provider == "together"
@pytest.mark.parametrize(
("model", "expected_provider"),
[
("groq/llama-3.3-70b", "groq"),
("cohere/command-r", "cohere"),
("sambanova/Meta-Llama-3.1-70B-Instruct", "sambanova"),
("mistral/mistral-large", "mistral"),
("vertex_ai/gemini-1.5-pro", "vertex_ai"),
("openai/custom-finetune-model", "openai"),
("anthropic/gpt-4o", "anthropic"),
],
)
def test_litellm_path_preserves_provider_from_model_prefix(model, expected_provider):
llm = LLM(model=model, is_litellm=False)
assert llm.is_litellm is True
assert llm.provider == expected_provider
assert llm.model == model
def test_litellm_keeps_provider_but_formats_multimodal_as_openai_schema():
llm = LLM(model="anthropic/claude-3-5-haiku-20241022", is_litellm=True)
assert llm.provider == "anthropic"
assert llm._multimodal_formatter_name() == "openai"
def test_unprefixed_models_use_native_sdk():

4
lib/crewai/tests/test_llm_streaming_finish_reason.py
View File

@@ -11,14 +11,14 @@ from unittest.mock import patch
import pytest
from crewai.events.event_bus import CrewAIEventsBus
from crewai.events.event_bus import crewai_event_bus
from crewai.events.types.llm_events import LLMCallCompletedEvent
from crewai.llm import LLM
@pytest.fixture
def mock_emit():
with patch.object(CrewAIEventsBus, "emit") as mock:
with patch.object(crewai_event_bus, "emit") as mock:
yield mock

18
lib/crewai/tests/utilities/test_converter.py
View File

@@ -1004,3 +1004,21 @@ def test_internal_instructor_omits_unset_base_url_and_api_key() -> None:
InternalInstructor(content="x", model=SimpleModel, llm=mock_llm)
mock_from_provider.assert_called_once_with("openai/gpt-4o")
def test_internal_instructor_does_not_double_prefix_qualified_models() -> None:
from crewai.utilities.internal_instructor import InternalInstructor
mock_llm = Mock()
mock_llm.is_litellm = False
mock_llm.model = "groq/llama-3.3-70b"
mock_llm.provider = "groq"
mock_llm.base_url = None
mock_llm.api_key = None
with patch("instructor.from_provider") as mock_from_provider:
mock_from_provider.return_value = Mock()
InternalInstructor(content="x", model=SimpleModel, llm=mock_llm)
mock_from_provider.assert_called_once_with("groq/llama-3.3-70b")

11
lib/crewai/tests/utilities/test_events.py
View File

@@ -1244,7 +1244,6 @@ def test_llm_completed_event_includes_usage():
assert event.usage.get("total_tokens", 0) > 0
@pytest.mark.vcr()
def test_llm_emits_call_failed_event():
received_events = []
event_received = threading.Event()
@@ -1256,12 +1255,10 @@ def test_llm_emits_call_failed_event():
error_message = "OpenAI API call failed: Simulated API failure"
with patch(
"crewai.llms.providers.openai.completion.OpenAICompletion._handle_completion"
) as mock_handle_completion:
mock_handle_completion.side_effect = Exception("Simulated API failure")
llm = LLM(model="gpt-4o-mini")
llm = LLM(model="gpt-4o-mini")
with patch.object(
llm, "_handle_completion", side_effect=Exception("Simulated API failure")
):
with pytest.raises(Exception) as exc_info:
llm.call("Hello, how are you?")