fixed changes related to max_tokens and processing http error codes like 400 properly (#574)

Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-257.local>
This commit is contained in:
Salman Paracha 2025-09-25 17:00:37 -07:00 committed by GitHub
parent 7ce8d44d8e
commit 03c2cf6f0d
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
6 changed files with 157 additions and 23 deletions

View file

@ -10,10 +10,13 @@ listeners:
llm_providers:
# OpenAI Models
- model: openai/gpt-4o-mini
- model: openai/gpt-5-mini-2025-08-07
access_key: $OPENAI_API_KEY
default: true
- model: openai/gpt-4o-mini
access_key: $OPENAI_API_KEY
- model: openai/o3
access_key: $OPENAI_API_KEY
@ -41,7 +44,7 @@ llm_providers:
model_aliases:
# Alias for summarization tasks -> fast/cheap model
arch.summarize.v1:
target: gpt-4o-mini
target: gpt-5-mini-2025-08-07
# Alias for general purpose tasks -> latest model
arch.v1:
@ -61,7 +64,7 @@ model_aliases:
# Semantic aliases
summary-model:
target: gpt-4o-mini
target: gpt-5-mini-2025-08-07
chat-model:
target: llama3.1