{"repo":"NousResearch/hermes-agent","public_id":"17913","display_label":"Ollama/local provider hang and timeout issues","summary":"Multiple bug reports and fixes related to indefinite hangs, stream timeouts, and connection issues when using local providers like Ollama, particularly with tool definitions and custom proxy setups. Associated fixes address stream timeout scaling, context probing behavior, and toolset configuration.","subsystem":"agent","counts":{"members":9,"open_issues":5,"open_issues_distinct":5,"open_prs":4,"closed_issues":0,"merged_prs":0,"attempt_prs":4},"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":0.1511111111111111},"fix_edges":[],"members":[{"kind":"issue","number":17913,"title":"OmniRoute compatibility: local custom providers can stall indefinitely on streamed chat completions","url":null,"state":"open"},{"kind":"issue","number":25629,"title":"[Bug]: Hermes Agent + Ollama Local — Hangs indefinitely with tool definitions","url":null,"state":"open"},{"kind":"issue","number":26339,"title":"[Bug] Connection reset by peer (errno 104) with Ollama local endpoint — 76KB payload rejected","url":null,"state":"open"},{"kind":"issue","number":26489,"title":"Hermes hangs when provider=custom + LiteLLM proxy + Ollama (no chat completion call after probing 404s)","url":null,"state":"open"},{"kind":"issue","number":56994,"title":"Requests to local Ollama models hang indefinitely with full CLI toolset (works via raw ollama run and cloud providers)","url":null,"state":"open"},{"kind":"pr","number":18703,"title":"fix(agent): keep local stream timeouts finite","url":null,"state":"open","close_reason":{"refs":[{"kind":"commit","value":"615ad97928f042d401b83142fd7d9daf50f48915","number":0},{"kind":"commit","value":"0430e71ec971d673a6d2a32fd54c1847683a16d2","number":0}],"category":"uncategorized","implication":"needs_llm"},"merged":false},{"kind":"pr","number":18716,"title":"fix(agent): scale stream timeouts by max_tokens output budget","url":null,"state":"open","close_reason":{"category":"uncategorized","implication":"needs_llm"},"merged":false},{"kind":"pr","number":25638,"title":"fix(ollama): skip local num_ctx probe for explicit chat completions","url":null,"state":"open","close_reason":{"refs":[{"kind":"commit","value":"9f408989c","number":0}],"category":"uncategorized","implication":"needs_llm"},"merged":false},{"kind":"pr","number":26347,"title":"fix(cli): honor legacy minimal toolset config","url":null,"state":"open","close_reason":{"category":"uncategorized","implication":"needs_llm"},"merged":false}],"trust":{"default_tier":"verified","includes_suggested":false}}