{"repo":"NousResearch/hermes-agent","public_id":"43900","display_label":"Ollama context window and API adapter issues","summary":"These items relate to Ollama integration: a bug where context is silently capped at 4096 tokens, a feature adding a native Ollama /api/chat adapter, and a fix for sending num_ctx correctly to the Ollama API.","subsystem":"agent","counts":{"members":3,"open_issues":1,"open_issues_distinct":1,"open_prs":2,"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":43900,"title":"[Bug] Ollama local models silently capped at 4096-token context — causes finish_reason=length and garbled retry responses","url":null,"state":"open"},{"kind":"pr","number":43995,"title":"fix(providers): send num_ctx at top-level for Ollama /v1/chat/completions","url":null,"state":"open","close_reason":{"refs":[{"kind":"pr","value":"#43900","number":43900}],"category":"uncategorized","implication":"needs_llm"},"merged":false},{"kind":"pr","number":73285,"title":"feat(agent): add native Ollama /api/chat adapter (#43900)","url":null,"state":"open","close_reason":{"refs":[{"kind":"pr","value":"#43900","number":43900}],"category":"implemented_elsewhere","implication":"superseded"},"merged":false}],"trust":{"default_tier":"verified","includes_suggested":false}}