LLM_TIMEOUT_MS default 60 s -> 3 min (v0.21.4)
CI / build + unit (pull_request) Failing after 21s

Production incident: '#rss get lublin' at 9:41 AM failed with 'The operation
was aborted due to timeout' — the LlmService call hit its 60 s cap while the
local OpenAI-compatible server (qwen3.8-27b, uncontrollable reasoning tokens)
was slow/busy. The same endpoint answers a trivial prompt in ~1 s when idle,
so this is latency variance on the server side, not a dead endpoint.

Bump the LLM_TIMEOUT_MS fallback from 60000 to 180000 (3 min headroom for
slow reasoning periods); still env-overridable, only the default changed.
This commit is contained in:
2026-09-26 09:52:18 +00:00
parent 0722c82359
commit 98b9ec5185
4 changed files with 8 additions and 4 deletions
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "mesh-bot",
"version": "0.21.3",
"version": "0.21.4",
"description": "",
"author": "",
"private": true,