Skip to content

docs(config): document DEFAULT_OCI_CHAT_MAX_TOKENS#320

Closed
fede-kamel wants to merge 1 commit into
BerriAI:mainfrom
fede-kamel:litellm_oci_default_max_tokens_doc
Closed

docs(config): document DEFAULT_OCI_CHAT_MAX_TOKENS#320
fede-kamel wants to merge 1 commit into
BerriAI:mainfrom
fede-kamel:litellm_oci_default_max_tokens_doc

Conversation

@fede-kamel

Copy link
Copy Markdown
Contributor

Documents the DEFAULT_OCI_CHAT_MAX_TOKENS environment variable in the config settings reference. It pairs with BerriAI/litellm#30018, which injects a default maxTokens for OCI GenAI chat when the caller omits max_tokens (OCI's server-side default truncates responses at ~20 tokens). The litellm test_env_keys.py documentation check validates every env var referenced in code against this table, so the new var has to be listed here for that check to pass

@vercel

vercel Bot commented Jun 9, 2026

Copy link
Copy Markdown

The latest updates on your projects. Learn more about Vercel for GitHub.

Project Deployment Actions Updated (UTC)
litellm Ready Ready Preview, Comment Jun 9, 2026 5:45pm

Request Review

@fede-kamel

Copy link
Copy Markdown
Contributor Author

Closing: litellm#30018 now uses a plain constant for DEFAULT_OCI_CHAT_MAX_TOKENS instead of an os.getenv override, so it no longer introduces a new env var that needs documenting here. No docs change required

@fede-kamel fede-kamel closed this Jun 9, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant