From 80f29321462a98e37e61714cc5bf1c4e6176dc76 Mon Sep 17 00:00:00 2001 From: mubashir1osmani Date: Fri, 31 Jul 2026 16:39:06 -0700 Subject: [PATCH] fix(batches): drop the env-var override for the input-file read timeout BATCH_INPUT_FILE_READ_TIMEOUT_SECONDS failed the documentation gate, which requires every env var to be documented in the environment-settings reference (that lives in the litellm-docs repo, not here). The env var was redundant anyway: general_settings.batch_input_file_read_timeout already makes the deadline configurable per deployment, which is what was asked for. Keeping only the general_settings key leaves one documented way to set it. --- litellm/constants.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/litellm/constants.py b/litellm/constants.py index 4c2d14dae02..4773c031422 100644 --- a/litellm/constants.py +++ b/litellm/constants.py @@ -1379,9 +1379,9 @@ BATCH_STATUS_POLL_MAX_ATTEMPTS = int(os.getenv("BATCH_STATUS_POLL_MAX_ATTEMPTS", # Deadline for the batch rate limiter's input-file read. The read happens inline # in POST /v1/batches, so it must resolve well within a client's read timeout; # unbounded, the OpenAI SDK default (600s, max_retries=2) applies and a stalled -# Files API holds the request open indefinitely. Override per-deployment with +# Files API holds the request open indefinitely. Override with # general_settings.batch_input_file_read_timeout. -DEFAULT_BATCH_INPUT_FILE_READ_TIMEOUT_SECONDS = float(os.getenv("BATCH_INPUT_FILE_READ_TIMEOUT_SECONDS", 10)) +DEFAULT_BATCH_INPUT_FILE_READ_TIMEOUT_SECONDS = 10.0 HEALTH_CHECK_TIMEOUT_SECONDS = int(os.getenv("HEALTH_CHECK_TIMEOUT_SECONDS", 60)) # 60 seconds _background_health_check_max_tokens_env = os.getenv("BACKGROUND_HEALTH_CHECK_MAX_TOKENS")