docs: Document custom timeout values
This commit is contained in:
@@ -36,6 +36,14 @@ OPENROUTER_API_KEY=your_openrouter_api_key_here
|
||||
# CUSTOM_API_KEY= # Empty for Ollama (no auth needed)
|
||||
# CUSTOM_MODEL_NAME=llama3.2 # Default model name
|
||||
|
||||
# Optional: HTTP timeout tuning for OpenAI-compatible endpoints (OpenRouter/custom/local)
|
||||
# Values are seconds; defaults are 45s connect / 900s read/write/pool for remote URLs
|
||||
# and 60s/1800s when pointing at localhost. Raise these if long-running models time out.
|
||||
# CUSTOM_CONNECT_TIMEOUT=45.0
|
||||
# CUSTOM_READ_TIMEOUT=900.0
|
||||
# CUSTOM_WRITE_TIMEOUT=900.0
|
||||
# CUSTOM_POOL_TIMEOUT=900.0
|
||||
|
||||
# Optional: Default model to use
|
||||
# Options: 'auto' (Claude picks best model), 'pro', 'flash', 'o3', 'o3-mini', 'o4-mini', 'o4-mini-high',
|
||||
# 'gpt-5', 'gpt-5-mini', 'grok', 'opus-4.1', 'sonnet-4.1', or any DIAL model if DIAL is configured
|
||||
|
||||
Reference in New Issue
Block a user