From b57a6dd9865ec7504577d3545d4bb0fef3a11673 Mon Sep 17 00:00:00 2001 From: Federico Kamelhar Date: Tue, 9 Jun 2026 14:21:21 -0400 Subject: [PATCH] fix(oci): make DEFAULT_OCI_CHAT_MAX_TOKENS a plain constant Drop the os.getenv override. The env knob was not requested and introducing a new env var forced a cross-repo dependency on litellm-docs (test_env_keys.py validates every referenced env var against the docs table there). A plain 4096 constant keeps the PR self-contained; callers who want a different limit pass max_tokens explicitly per request. --- litellm/constants.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/litellm/constants.py b/litellm/constants.py index 1d85183f26c..b54dec024fd 100644 --- a/litellm/constants.py +++ b/litellm/constants.py @@ -418,7 +418,7 @@ REPLICATE_POLLING_DELAY_SECONDS = float( DEFAULT_ANTHROPIC_CHAT_MAX_TOKENS = int( os.getenv("DEFAULT_ANTHROPIC_CHAT_MAX_TOKENS", 4096) ) -DEFAULT_OCI_CHAT_MAX_TOKENS = int(os.getenv("DEFAULT_OCI_CHAT_MAX_TOKENS", 4096)) +DEFAULT_OCI_CHAT_MAX_TOKENS = 4096 TOGETHER_AI_4_B = int(os.getenv("TOGETHER_AI_4_B", 4)) TOGETHER_AI_8_B = int(os.getenv("TOGETHER_AI_8_B", 8)) TOGETHER_AI_21_B = int(os.getenv("TOGETHER_AI_21_B", 21))