diff --git a/ollama/docker-compose.yml b/ollama/docker-compose.yml
index 18bc455..ce20fb6 100644
--- a/ollama/docker-compose.yml
+++ b/ollama/docker-compose.yml
@@ -17,6 +17,13 @@ services:
       # attention + an explicitly quantized KV cache keep it small and stable.
       - OLLAMA_FLASH_ATTENTION=1
       - OLLAMA_KV_CACHE_TYPE=q8_0
+      # Server-level default context, kept in step with SUB/WAVE's own
+      # llm.numCtx (settings.json) -- 11264 is the largest value that still
+      # fits the full 29-layer GPU offload on this 6GB card with margin, while
+      # staying above the ~7.5k-token peak seen in real multi-turn DJ-agent
+      # calls (a lower ceiling truncates the front of the prompt -- including
+      # the tool definitions -- and the agent stops calling `done`, #291).
+      - OLLAMA_CONTEXT_LENGTH=11264
     volumes:
       - /srv/ollama:/root/.ollama
     runtime: nvidia