Merge branch 'main' into feat-rag-databases

Reviewed-on: #50

.env.example

@@ -105,34 +105,6 @@ COMFYUI_PGID=
 HOST_VIDEO_GID=
 HOST_RENDER_GID=
 
-# --- llama.cpp / fast model (second, always-resident instance — see
-# docs/research/fast-model-choice.md and issue #44) ---
-# Qwen3-4B-Instruct-2507: architecturally non-thinking (never emits
-# <think> blocks, unlike Qwen3-1.7B/0.6B which need a per-call toggle) —
-# picked specifically so it stays fast enough for qwen-code's Auto Mode
-# classifier (Stage 1 wants ~300ms). Same publisher (unsloth) as the main
-# model for consistency.
-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
-# --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=1
-
 # --- ComfyUI diffusion model (Qwen-Image, FP8 — see docs/research/
 # image-generation-model-choice.md and issue #42) ---
 # Three files: diffusion weights, text encoder, VAE — all from the official

docker-compose.yml

@@ -15,8 +15,7 @@ services:
     ipc: host
     # Caps this process's HIP hardware-queue allocation — works around
     # ROCm/ROCm#5706 (GPU pinned at 100%/boost-clock whenever two
-    # concurrent HIP contexts touch this card, confirmed on real hardware
+    # concurrent HIP contexts touch this card). See the research doc above.
-    # against llama-server-fast below). See the research doc above.
     environment:
       - GPU_MAX_HW_QUEUES=1
     volumes:
@@ -47,49 +46,6 @@ services:
       - "lazytainer.group.llamaserver.inactiveTimeout=${LAZYTAINER_INACTIVE_TIMEOUT:-900}"
       - "lazytainer.group.llamaserver.minPacketThreshold=2"
 
-  llama-server-fast:
-    image: ghcr.io/ggml-org/llama.cpp:server-rocm
-    container_name: llama-server-fast
-    devices:
-      - /dev/kfd
-      - /dev/dri
-    group_add:
-      - "${HOST_VIDEO_GID:?run scripts/update.sh first to resolve this}"
-      - "${HOST_RENDER_GID:?run scripts/update.sh first to resolve this}"
-    security_opt:
-      - seccomp=unconfined
-    ipc: host
-    # See llama-server's identical setting above — same fix, same bug.
-    environment:
-      - GPU_MAX_HW_QUEUES=1
-    volumes:
-      - models:/models
-    command: >
-      -m /models/${LLAMA_FAST_MODEL_FILE:-Qwen3-4B-Instruct-2507-UD-Q8_K_XL.gguf}
-      --host 0.0.0.0
-      --port 8080
-      --n-gpu-layers ${LLAMA_FAST_GPU_LAYERS:-999}
-      --ctx-size ${LLAMA_FAST_CTX_SIZE:-8192}
-      --parallel ${LLAMA_FAST_PARALLEL:-1}
-      --flash-attn on
-      --cache-type-k q8_0
-      --cache-type-v q8_0
-      --reasoning off
-      --jinja
-    # Second, always-resident llama.cpp instance — small non-thinking model
-    # used as qwen-code's Auto Mode classifier fastModel, alongside the main
-    # 27B instance above. See docs/research/fast-model-choice.md and #44.
-    # Same ai-stack-only pattern as llama-server: no published host port.
-    expose:
-      - "8080"
-    restart: unless-stopped
-    networks: [ai-stack]
-    labels:
-      - "lazytainer.group.llamaserverfast.sleepMethod=stop"
-      - "lazytainer.group.llamaserverfast.ports=8080"
-      - "lazytainer.group.llamaserverfast.inactiveTimeout=${LAZYTAINER_INACTIVE_TIMEOUT:-900}"
-      - "lazytainer.group.llamaserverfast.minPacketThreshold=2"
-
   # ponytail: one-off downloader, not a standing service — run via
   # `docker compose --profile tools run --rm downloader`. Folded into
   # scripts/update.sh, which runs this every time; the `test -f` guard is
@@ -111,26 +67,9 @@ services:
         curl -L --fail --create-dirs -o /models/${LLAMA_MODEL_FILE:-Qwen3.8-27B-UD-Q4_K_XL.gguf}
         https://huggingface.co/unsloth/Qwen3.8-27B-GGUF/resolve/main/${LLAMA_MODEL_FILE:-Qwen3.8-27B-UD-Q4_K_XL.gguf}
 
-  # Same test -f guard pattern as downloader above — fetches the second,
-  # smaller model for llama-server-fast. See issue #44.
-  downloader-fast:
-    image: curlimages/curl:latest
-    profiles: ["tools"]
-    user: root
-    volumes:
-      - models:/models
-    entrypoint: ["sh", "-c"]
-    command:
-      - >
-        test -f /models/${LLAMA_FAST_MODEL_FILE:-Qwen3-4B-Instruct-2507-UD-Q8_K_XL.gguf} &&
-        echo "already downloaded, skipping" ||
-        curl -L --fail --create-dirs -o /models/${LLAMA_FAST_MODEL_FILE:-Qwen3-4B-Instruct-2507-UD-Q8_K_XL.gguf}
-        https://huggingface.co/unsloth/Qwen3-4B-Instruct-2507-GGUF/resolve/main/${LLAMA_FAST_MODEL_FILE:-Qwen3-4B-Instruct-2507-UD-Q8_K_XL.gguf}
-
   # Fetches the three Qwen-Image FP8 files ComfyUI needs (diffusion model,
-  # text encoder, VAE) — same test -f guard pattern as downloader/
+  # text encoder, VAE) — same test -f guard pattern as downloader above.
-  # downloader-fast above. See docs/research/image-generation-model-choice.md
+  # See docs/research/image-generation-model-choice.md and issue #42.
-  # and issue #42.
   #
   # ponytail: target paths assume ComfyUI's standard models/ layout under
   # BASE_STORAGE_PATH (/storage) — same "not independently confirmed against
@@ -184,7 +123,7 @@ services:
       # This image also wants GID env vars directly (its own README asks
       # for both these and group_add above) — same HOST_VIDEO_GID/
       # HOST_RENDER_GID resolved by scripts/update.sh, shared with
-      # llama-server/llama-server-fast now instead of comfyui-only vars.
+      # llama-server now instead of comfyui-only vars.
       - PUID=${COMFYUI_PUID}
       - PGID=${COMFYUI_PGID}
       - VIDEO_GID=${HOST_VIDEO_GID}
@@ -220,8 +159,6 @@ services:
     depends_on:
       llama-server:
         condition: service_started
-      llama-server-fast:
-        condition: service_started
     volumes:
       - omniroute-data:/app/data
     env_file: .env

scripts/switch-model.sh

@@ -11,12 +11,6 @@
 # it never reliably sleeps a service on its own. A scripted swap always
 # knows which service should go up/down, so it doesn't need that heuristic.
 #
-# llama-server-fast (the small classifier model, issue #44) is NOT part of
-# this swap — it's meant to stay always-resident. Worst case with comfyui up
-# is comfyui (~25GB, Qwen-Image FP8) + llama-server-fast (~5GB) ≈ 30GB,
-# still under the 32GB card but tight — unverified on real hardware, check
-# `docker compose ps` / VRAM usage after the first real swap.
-#
 # OmniRoute may show the just-stopped provider as errored/offline in its
 # dashboard for up to CREDENTIAL_HEALTH_CHECK_INTERVAL (default 5 min) after
 # a swap — cosmetic, not a functional problem (see the research doc above).