{"repo":"NousResearch/hermes-agent","public_id":"21566","display_label":"Auxiliary LLM client timeouts for slow local endpoints","summary":"The members share one theme: the auxiliary LLM client's default timeout (reported as 30s) is described as too short for slow local inference, with reports of retry storms and compression problems. Several members are proposed changes that raise or auto-adjust the timeout, including detection of local endpoints and a 300s setting.","subsystem":"agent","counts":{"members":5,"open_issues":1,"open_issues_distinct":1,"open_prs":1,"closed_issues":1,"merged_prs":0,"attempt_prs":3},"landed_fix":null,"resolution":{"state":"unresolved","by":null},"freshness":{"state":"never_verified","last_verified_at":null,"is_stale":false},"grouping":{"backbone":"STRUCTURAL_PARTIAL","link_density":0.33599999999999997},"fix_edges":[],"members":[{"kind":"issue","number":21566,"title":"Auxiliary LLM calls (session_search, skills_hub, etc.) use short 30s default timeout with no local-endpoint detection — causes retry storms on slow local inference","url":null,"state":"open"},{"kind":"issue","number":35517,"title":"[Bug]: Auxiliary client HTTP timeout defaults to 30s, causing compression to fail with slow local LLMs","url":null,"state":"closed"},{"kind":"pr","number":21569,"title":"fix(agent): auto-bump auxiliary LLM timeout for local endpoints","url":null,"state":"open","close_reason":{"refs":[{"kind":"pr","value":"#21575","number":21575},{"kind":"pr","value":"#21566","number":21566}],"category":"uncategorized","implication":"needs_llm"},"merged":false},{"kind":"pr","number":21575,"title":"fix(auxiliary): bump aux-call timeout for local endpoints (#21566)","url":null,"state":"closed","close_reason":{"category":"stale_abandoned","implication":"active"},"merged":false},{"kind":"pr","number":36258,"title":"fix(agent): add 300s timeout to all auxiliary OpenAI clients (#35517)","url":null,"state":"closed","close_reason":{"refs":[{"kind":"commit","value":"370a489fb4adb7268f6510439e25e8213bddb624","number":0}],"category":"implemented_elsewhere","implication":"superseded"},"merged":false}],"trust":{"default_tier":"verified","includes_suggested":false}}