{"repo":"NousResearch/hermes-agent","public_id":"109606","display_label":"Fix latency estimates for local model recommendations","summary":"These items address a bug where local model speed recommendations ignored prompt prefill time, which accounts for the majority of wall-clock time per agent turn. Fixes aim to stop recommending models with misleadingly slow real-world performance.","subsystem":"hermes_cli","counts":{"members":3,"open_issues":1,"open_issues_distinct":1,"open_prs":1,"closed_issues":0,"merged_prs":0,"attempt_prs":2},"landed_fix":null,"resolution":{"state":"unresolved","by":null},"freshness":{"state":"never_verified","last_verified_at":null,"is_stale":false},"grouping":{"backbone":"STRUCTURAL_SPANNING","link_density":0.6666666666666666},"fix_edges":[],"members":[{"kind":"issue","number":109606,"title":"[Bug]: Local Models speed gate models decode only — the prompt prefill it omits is 87-93% of an agent turn's wall clock","url":null,"state":"open"},{"kind":"pr","number":109618,"title":"fix(local-runtime): price recommendations by turn latency","url":null,"state":"closed","close_reason":{"refs":[{"kind":"commit","value":"2cbf4bf0444b6d15313e82ccf05220cdff36eddd","number":0},{"kind":"commit","value":"3569e8461ea721623fa16e6f01fb636157989fe6","number":0},{"kind":"pr","value":"#109606","number":109606},{"kind":"pr","value":"#109618","number":109618}],"category":"uncategorized","implication":"needs_llm"},"merged":false},{"kind":"pr","number":109630,"title":"fix(local-runtime): stop recommending models with multi-minute prompt waits","url":null,"state":"open","close_reason":{"refs":[{"kind":"commit","value":"be0a48ed895d328651ad60bad6f421ddbc6cd54d","number":0},{"kind":"commit","value":"6f1e791831db01188ec7e11b440c3bd5a57c0095","number":0}],"category":"wontfix_bydesign","implication":"wontfix"},"merged":false}],"trust":{"default_tier":"verified","includes_suggested":false}}