mirror of
https://github.com/tiennm99/litellm.git
synced 2026-06-18 00:48:01 +00:00
Sameer Kankute
cc650f4865
Spend logs are written asynchronously in batches, so a DB lookup for a just-completed response's spend log races and returns zero rows. Replace the DB-only fallback with an in-memory session store (_session_history) that is populated after each response.completed event and consulted at the start of the next response.create. This makes same-connection multi-turn reliable without any timing dependency on the DB write queue. Made-with: Cursor
20 lines
888 B
TOML
20 lines
888 B
TOML
lint.ignore = ["F405", "E402", "E501", "F403"]
|
|
lint.extend-select = ["E501", "PLR0915", "T20"]
|
|
line-length = 120
|
|
exclude = ["litellm/types/*", "litellm/__init__.py", "litellm/proxy/example_config_yaml/*", "tests/*"]
|
|
|
|
|
|
[lint.per-file-ignores]
|
|
"litellm/main.py" = ["F401"]
|
|
"litellm/utils.py" = ["F401"]
|
|
"litellm/proxy/proxy_server.py" = ["F401"]
|
|
"litellm/caching/__init__.py" = ["F401"]
|
|
"litellm/llms/anthropic/chat/__init__.py" = ["F401"]
|
|
"litellm/llms/azure_ai/embed/__init__.py" = ["F401"]
|
|
"litellm/llms/azure_ai/rerank/__init__.py" = ["F401"]
|
|
"litellm/llms/bedrock/chat/__init__.py" = ["F401"]
|
|
"litellm/proxy/utils.py" = ["F401", "PLR0915"]
|
|
"litellm/proxy/guardrails/guardrail_hooks/litellm_content_filter/content_filter.py" = ["PLR0915"]
|
|
"litellm/proxy/guardrails/guardrail_hooks/guardrail_benchmarks/test_eval.py" = ["PLR0915"]
|
|
"litellm/responses/streaming_iterator.py" = ["PLR0915"]
|