scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-10 03:28:53 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 84

fix(constants): fix missing comma, wrong cost multiplier, and duplicate constant

Browse source 
- Add missing comma in clarifai_models between Qwen3-30B and gpt-5-nano entries
- Correct AZURE_COMPUTER_USE cost defaults from 3.0/12.0 to 0.003/0.012 (1000x overcharge)
- Remove duplicate MAX_SIZE_PER_ITEM_IN_MEMORY_CACHE_IN_KB definition (512) that overwrote the intended 1024

Fixes #25140
This commit is contained in:
nightcityblade 2026-04-05 23:35:00 +08:00
parent d251238bd7
commit 712d63bd10
2 changed files with 43 additions and 6 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

9
litellm/constants.py
View file

@ -307,12 +307,12 @@ AZURE_FILE_SEARCH_COST_PER_GB_PER_DAY = float(
)
AZURE_COMPUTER_USE_INPUT_COST_PER_1K_TOKENS = float(
os.getenv(
"AZURE_COMPUTER_USE_INPUT_COST_PER_1K_TOKENS", 3.0
"AZURE_COMPUTER_USE_INPUT_COST_PER_1K_TOKENS", 0.003
) # $0.003 USD per 1K Tokens
)
AZURE_COMPUTER_USE_OUTPUT_COST_PER_1K_TOKENS = float(
os.getenv(
"AZURE_COMPUTER_USE_OUTPUT_COST_PER_1K_TOKENS", 12.0
"AZURE_COMPUTER_USE_OUTPUT_COST_PER_1K_TOKENS", 0.012
) # $0.012 USD per 1K Tokens
)
AZURE_VECTOR_STORE_COST_PER_GB_PER_DAY = float(
@ -388,9 +388,6 @@ CACHED_STREAMING_CHUNK_DELAY = float(os.getenv("CACHED_STREAMING_CHUNK_DELAY", 0
AUDIO_SPEECH_CHUNK_SIZE = int(
os.getenv("AUDIO_SPEECH_CHUNK_SIZE", 8192)
) # chunk_size for audio speech streaming. Balance between latency and memory usage
MAX_SIZE_PER_ITEM_IN_MEMORY_CACHE_IN_KB = int(
os.getenv("MAX_SIZE_PER_ITEM_IN_MEMORY_CACHE_IN_KB", 512)
)
DEFAULT_MAX_TOKENS_FOR_TRITON = int(os.getenv("DEFAULT_MAX_TOKENS_FOR_TRITON", 2000))
#### Networking settings ####
request_timeout: float = float(os.getenv("REQUEST_TIMEOUT", 6000)) # time in seconds
@ -840,7 +837,7 @@ clarifai_models: set = set(
"clarifai/qwen.qwenLM.Qwen3-30B-A3B-Instruct-2507",
"clarifai/qwen.qwen3.qwen3-next-80B-A3B-Thinking",
"clarifai/openai.chat-completion.gpt-oss-120b",
"clarifai/qwen.qwenLM.Qwen3-30B-A3B-Thinking-2507"
"clarifai/qwen.qwenLM.Qwen3-30B-A3B-Thinking-2507",
"clarifai/openai.chat-completion.gpt-5-nano",
"clarifai/openai.chat-completion.gpt-4o",
"clarifai/gcp.generate.gemini-2_5-pro",

40
tests/test_litellm/test_constants_fixes.py Normal file
View file

@ -0,0 +1,40 @@
"""Tests for constants.py fixes (issue #25140)."""
import ast
import re
def test_clarifai_models_no_implicit_concatenation():
"""Ensure clarifai_models entries are properly comma-separated (no implicit string concatenation)."""
with open("litellm/constants.py") as f:
content = f.read()
# The two strings that were previously concatenated due to missing comma
assert "clarifai/qwen.qwenLM.Qwen3-30B-A3B-Thinking-2507" in content
assert "clarifai/openai.chat-completion.gpt-5-nano" in content
# Verify comma exists between them
pattern = r'"clarifai/qwen\.qwenLM\.Qwen3-30B-A3B-Thinking-2507"\s*,\s*\n\s*"clarifai/openai\.chat-completion\.gpt-5-nano"'
assert re.search(pattern, content), "Missing comma between clarifai model entries"
def test_azure_computer_use_cost_defaults():
"""Ensure Azure Computer Use cost defaults match documented values ($0.003/$0.012 per 1K tokens)."""
with open("litellm/constants.py") as f:
content = f.read()
assert '"AZURE_COMPUTER_USE_INPUT_COST_PER_1K_TOKENS", 0.003' in content
assert '"AZURE_COMPUTER_USE_OUTPUT_COST_PER_1K_TOKENS", 0.012' in content
def test_no_duplicate_max_size_per_item_in_memory_cache():
"""Ensure MAX_SIZE_PER_ITEM_IN_MEMORY_CACHE_IN_KB is defined only once."""
with open("litellm/constants.py") as f:
content = f.read()
definitions = re.findall(
r"^MAX_SIZE_PER_ITEM_IN_MEMORY_CACHE_IN_KB\s*=", content, re.MULTILINE
)
assert len(definitions) == 1, (
f"Expected 1 definition, found {len(definitions)}"
)