admin/openhuman
1
0
Fork 0
mirror of https://github.com/tinyhumansai/openhuman.git synced 2026-07-27 21:08:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat(inference): make compatible-provider HTTP timeouts configurable (#3856) (#3864)

Browse Source 
Co-authored-by: Steven Enamakel <enamakel@tinyhumans.ai>
This commit is contained in:
Hüsam
2026-06-22 17:29:28 +05:30
committed by GitHub
co-authored by Steven Enamakel
parent b8b69da776
commit 0db261dcc2
4 changed files with 141 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.env.example
+7
View File
@@ -101,6 +101,13 @@ OPENHUMAN_TEMPERATURE=0.7
# in-app "Action timeout" setting (Settings -> Agent OS access), which persists
# to [agent].agent_timeout_secs. Leave unset to let the UI control it.
# OPENHUMAN_TOOL_TIMEOUT_SECS=
# [optional] Operator override for the inference HTTP request timeout, in
# seconds (default 120, range 1-3600). Raise this when long reasoning/research
# turns get cut off at the two-minute mark. Leave unset to use the default.
# OPENHUMAN_INFERENCE_TIMEOUT_SECS=
# [optional] Operator override for the inference HTTP connection-establishment
# timeout, in seconds (default 10, range 1-300). Leave unset to use the default.
# OPENHUMAN_INFERENCE_CONNECT_TIMEOUT_SECS=
# [optional] Headless update restart contract: self_replace | supervisor
# OPENHUMAN_AUTO_UPDATE_RESTART_STRATEGY=self_replace
# [optional] Allow bearer-authenticated RPC callers to invoke update.apply/update.run