feat(llm): re-enable RAM prompt cache (8192 MiB) with --no-cache-idle-slots

--no-cache-idle-slots is the llama.cpp#27148 mitigation for --kv-unified,
which was the cause of misspelled output with --cache-ram on.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

docker-compose.yml

@@ -27,7 +27,8 @@ services:
       --flash-attn on
       --cache-type-k ${LLAMA_KV_CACHE_TYPE:-q8_0}
       --cache-type-v ${LLAMA_KV_CACHE_TYPE:-q8_0}
-      --cache-ram ${LLAMA_CACHE_RAM:-24576}
+      --cache-ram ${LLAMA_CACHE_RAM:-8192}
+      --no-cache-idle-slots
       ${LLAMA_SPEC_ARGS:-}
       --jinja
     # see docs/architecture.md#llama-server (flags), docs/network-access.md#backends (no host port)