{"repo":"NousResearch/hermes-agent","public_id":"15558","display_label":"Token budget recalculation bug on model switch","summary":"These issues and PRs address a bug where ContextCompressor's update_model() does not recalculate tail_token_budget and max_summary_tokens when the model changes, leaving stale values. The members consistently describe the problem and proposed fixes for this specific staleness issue.","subsystem":null,"counts":{"members":3,"open_issues":0,"open_issues_distinct":0,"open_prs":0,"closed_issues":1,"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":15558,"title":"[Bug]: update_model() leaves tail_token_budget and max_summary_tokens stale after model switch","url":null,"state":"closed"},{"kind":"pr","number":14630,"title":"fix: recalculate token budgets on model switch in ContextCompressor","url":null,"state":"closed","close_reason":{"category":"merged_via","implication":"superseded"},"merged":false,"is_fix_pr":true,"fix_tier":"suggested","fix_detail_withheld":true},{"kind":"pr","number":15560,"title":"fix(compressor): re-derive tail_token_budget and max_summary_tokens in update_model()","url":null,"state":"closed","close_reason":{"refs":[{"kind":"pr","value":"#14630","number":14630},{"kind":"pr","value":"#15558","number":15558}],"category":"uncategorized","implication":"needs_llm"},"merged":false,"is_fix_pr":true,"fix_tier":"suggested","fix_detail_withheld":true}],"trust":{"default_tier":"verified","includes_suggested":false}}