{"repo":"NousResearch/hermes-agent","public_id":"10368","display_label":"Model switching and session cache sync issues","summary":"Multiple bug reports and fixes related to model configuration changes not propagating to active sessions, stale model caches persisting after resets or switches, and UI state falling out of sync with the actual model being used across gateway, desktop, and CLI contexts.","subsystem":"agent","counts":{"members":9,"open_issues":2,"open_issues_distinct":2,"open_prs":2,"closed_issues":4,"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_PARTIAL","link_density":0.13333333333333336},"fix_edges":[],"members":[{"kind":"issue","number":10368,"title":"[Bug]: 切换模型后，没实时刷新缓存？导致AI继续以为自己还是上一个模型","url":null,"state":"closed"},{"kind":"issue","number":20628,"title":"Title: [Feature Request] Dynamic Model Switching for Gateway Platforms","url":null,"state":"closed"},{"kind":"issue","number":45689,"title":"[Bug] 桌面端模型切换路由不同步：右下角 UI 选 deepseek 实际仍走千问","url":null,"state":"closed"},{"kind":"issue","number":48840,"title":"[Bug] 网关显示异常 + 模型名未随配置更新（UI刷新不同步）","url":null,"state":"open"},{"kind":"issue","number":58403,"title":"/new doesn't reset model config — old session keeps using stale model after config change","url":null,"state":"closed"},{"kind":"issue","number":67120,"title":"Changing model via SSH/hermes config no longer propagates to active gateway sessions after update","url":null,"state":"open"},{"kind":"pr","number":45936,"title":"fix: use config.set for desktop model switches","url":null,"state":"open","close_reason":{"refs":[{"kind":"commit","value":"ce5c1f9f79a5735e6ac154903ef93782261b9c87","number":0},{"kind":"commit","value":"cb6b4127e795e55bdd7ae4fe35a0ff3cd9f53736","number":0}],"category":"uncategorized","implication":"needs_llm"},"merged":false},{"kind":"pr","number":48872,"title":"Fix Ollama TUI inventory/runtime sync","url":null,"state":"open","close_reason":{"category":"uncategorized","implication":"needs_llm"},"merged":false},{"kind":"pr","number":58431,"title":"fix(gateway): clear last-resolved-model cache on /new and compression auto-reset","url":null,"state":"closed","close_reason":{"category":"silent_close","implication":"active"},"merged":false}],"trust":{"default_tier":"verified","includes_suggested":false}}