From 22009e90a4576764687328ed3cf81efbd2813d77 Mon Sep 17 00:00:00 2001
From: Florian <2320560+florianbuetow@users.noreply.github.com>
Date: Sat, 31 Jan 2026 23:48:38 +0100
Subject: feat: add configurable request timeout for LLM calls

Local LLMs (LM Studio, Ollama, etc.) often need more than the default
30-second timeout. Added request_timeout config option (in seconds)
to [general] section and HEXAI_REQUEST_TIMEOUT env var.

Original constructor signatures preserved via *WithTimeout variants,
so no test changes required.
---
 docs/configuration.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'docs')

diff --git a/docs/configuration.md b/docs/configuration.md
index 50dfbcb..54ac85f 100644
--- a/docs/configuration.md
+++ b/docs/configuration.md
@@ -12,7 +12,7 @@ Environment overrides
 - All options can be overridden by environment variables prefixed with `HEXAI_`.
 - Env values take precedence over the config file.
 - Examples:
-  - `HEXAI_PROVIDER`, `HEXAI_MAX_TOKENS`, `HEXAI_CONTEXT_MODE`, `HEXAI_CONTEXT_WINDOW_LINES`, `HEXAI_MAX_CONTEXT_TOKENS`, `HEXAI_LOG_PREVIEW_LIMIT`
+  - `HEXAI_PROVIDER`, `HEXAI_MAX_TOKENS`, `HEXAI_CONTEXT_MODE`, `HEXAI_CONTEXT_WINDOW_LINES`, `HEXAI_MAX_CONTEXT_TOKENS`, `HEXAI_LOG_PREVIEW_LIMIT`, `HEXAI_REQUEST_TIMEOUT`
   - `HEXAI_CODING_TEMPERATURE`
   - `HEXAI_COMPLETION_DEBOUNCE_MS`, `HEXAI_COMPLETION_THROTTLE_MS`
   - `HEXAI_TRIGGER_CHARACTERS` (comma-separated, e.g., `".,:,_ , "`)
-- 
cgit v1.2.3