.env.example

@@ -116,11 +116,22 @@ LLAMA_FAST_MODEL_FILE=Qwen3-4B-Instruct-2507-UD-Q8_K_XL.gguf
 # Same reasoning as LLAMA_GPU_LAYERS above — full GPU offload, this model
 # is dense too.
 LLAMA_FAST_GPU_LAYERS=999
-# Classifier transcripts are truncated/bounded by qwen-code itself (see its
-# own Auto Mode docs) — no need for anywhere near the 27B's huge context.
-# 8192 keeps this instance's KV cache negligible.
+# --ctx-size is the TOTAL across every LLAMA_FAST_PARALLEL slot, not per
+# request — same halving already called out for the main model above.
+# Was PARALLEL=2, silently halving this to 4096/slot — too small: a real
+# classifier call (hints + environment + recent tool-call history) hit
+# "exceeds the available context size (4096 tokens)" in practice, which
+# qwen-code surfaces as "Auto Mode couldn't classify this action
+# (Classifier stage 1 unavailable)" — see issue #5. Fixed by dropping to
+# a single slot instead of raising ctx-size (no extra VRAM, and this
+# service doesn't need concurrent classifier calls the way the main
+# model needs concurrent chat sessions) — the full 8192 now goes to the
+# one slot. If hints.allow/softDeny/hardDeny ever approach their
+# 50-entries-each ceiling, raise LLAMA_FAST_CTX_SIZE instead — qwen-code
+# caps those at 200 chars x 150 entries plus 40,000 chars of
+# historical-action context, which can exceed 8192 tokens worst-case.
 LLAMA_FAST_CTX_SIZE=8192
-LLAMA_FAST_PARALLEL=2
+LLAMA_FAST_PARALLEL=1
 
 # --- ComfyUI diffusion model (Qwen-Image, FP8 — see docs/research/
 # image-generation-model-choice.md and issue #42) ---

docker-compose.yml

@@ -70,7 +70,7 @@ services:
       --port 8080
       --n-gpu-layers ${LLAMA_FAST_GPU_LAYERS:-999}
       --ctx-size ${LLAMA_FAST_CTX_SIZE:-8192}
-      --parallel ${LLAMA_FAST_PARALLEL:-2}
+      --parallel ${LLAMA_FAST_PARALLEL:-1}
       --flash-attn on
       --cache-type-k q8_0
       --cache-type-v q8_0