{"repo":"NousResearch/hermes-agent","public_id":"6611","display_label":"Requests for native vision/multimodal input support","summary":"Two feature requests ask for native image or multimodal input handling: one for the moonshot/kimi-k2.5 model, and one to replace the vision_analyze tool with native multimodal input. The titles suggest a shared theme, but no further detail is available.","subsystem":"agent","counts":{"members":2,"open_issues":1,"open_issues_distinct":1,"open_prs":0,"closed_issues":1,"merged_prs":0,"attempt_prs":0},"landed_fix":null,"resolution":{"state":"unresolved","by":null},"freshness":{"state":"never_verified","last_verified_at":null,"is_stale":false},"grouping":{"backbone":"LLM_ONLY","link_density":0.36},"fix_edges":[],"members":[{"kind":"issue","number":6611,"title":"[Feature Request]: Enable native vision support for moonshot/kimi-k2.5","url":null,"state":"open"},{"kind":"issue","number":7641,"title":"[Feature Request] Native multimodal input instead of vision_analyze tool","url":null,"state":"closed"}],"trust":{"default_tier":"verified","includes_suggested":false}}