{"repo":"NousResearch/hermes-agent","public_id":"37151","display_label":"max_completion_tokens parameter support for specific models","summary":"These issues and pull requests address using the correct max_completion_tokens parameter for MiniMax and GPT-5/o-series models instead of the legacy max_tokens parameter. The changes target specific model families and provider paths to ensure proper token limit handling.","subsystem":"agent","counts":{"members":4,"open_issues":1,"open_issues_distinct":1,"open_prs":1,"closed_issues":0,"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_SPANNING","link_density":0.5},"fix_edges":[],"members":[{"kind":"issue","number":37151,"title":"_max_tokens_param should use max_completion_tokens for MiniMax models","url":null,"state":"open"},{"kind":"pr","number":37152,"title":"fix(agent): use max_completion_tokens for MiniMax","url":null,"state":"open","close_reason":{"refs":[{"kind":"commit","value":"19c07c403","number":0}],"category":"uncategorized","implication":"needs_llm"},"merged":false},{"kind":"pr","number":43163,"title":"fix(agent): use max_completion_tokens for gpt-5.x and o-series models regardless of provider path","url":null,"state":"closed","close_reason":{"refs":[{"kind":"commit","value":"19c07c40379ba711e9db6a522bd0b7454d9d971f","number":0}],"category":"implemented_elsewhere","implication":"superseded"},"merged":false,"is_fix_pr":true,"fix_tier":"suggested","fix_detail_withheld":true},{"kind":"pr","number":124204,"title":"fix(params): use max_completion_tokens for MiniMax OpenAI-compat (#37151)","url":null,"state":"closed","close_reason":{"category":"uncategorized","implication":"needs_llm"},"merged":false}],"trust":{"default_tier":"verified","includes_suggested":false}}