From 462ca7c112d3cfb10593898db70b324ccd9b023f Mon Sep 17 00:00:00 2001
From: teknium1 <127238744+teknium1@users.noreply.github.com>
Date: Tue, 15 Sep 2026 11:39:13 -0700
Subject: [PATCH] docs(config): explicit ollama_num_ctx is never capped by
 context_length

agent/agent_init.py::_configure_ollama_num_ctx caps only the auto-detected
value (the cap is skipped when an explicit override is set). The salvaged
example wording said context_length caps the explicit value too, which
would send readers chasing a cap that does not apply.
---
 cli-config.yaml.example | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/cli-config.yaml.example b/cli-config.yaml.example
index 4f4b323d6f..dfaeed15d8 100644
--- a/cli-config.yaml.example
+++ b/cli-config.yaml.example
@@ -113,8 +113,9 @@ model:
   #
   # ollama_num_ctx: Ollama only — the num_ctx sent on every chat request.
   #   Hermes auto-detects the model's window and sends it (Ollama otherwise
-  #   defaults to 2048); set this to cap VRAM use. context_length, if set,
-  #   caps it further.
+  #   defaults to 2048); context_length, if set, caps the detected value.
+  #   An explicit ollama_num_ctx is sent as-is (never capped) — set it to
+  #   pin VRAM use.
   #
   # ollama_num_ctx: 32768
   #