refactor(models): merge downloaders into one, driven by models.yml

Replace the per-model downloader services with a single downloader
that reads file/url pairs from models.yml. Downloads now go to a
.part file first, so an interrupted run can't leave a truncated
model that later runs skip.

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

docker-compose.yml

@@ -38,34 +38,24 @@ services:
     restart: unless-stopped
     networks: [ai-stack]
 
-  # see docs/operations.md#model-downloads (also covers downloader-classifier)
+  # see docs/operations.md#model-downloads; the list of files is models.yml
   downloader:
-    image: curlimages/curl:latest
+    image: alpine:3
     profiles: ["tools"]
     user: root
     volumes:
       - models:/models
-    entrypoint: ["sh", "-c"]
+      - ./models.yml:/models.yml:ro
+    entrypoint: ["sh", "-euo", "pipefail", "-c"]
     command:
-      - >
-        test -f /models/${LLAMA_MODEL_FILE:-Qwen3.8-27B-UD-Q4_K_XL.gguf} &&
-        echo "already downloaded, skipping" ||
-        curl -L --fail --create-dirs -o /models/${LLAMA_MODEL_FILE:-Qwen3.8-27B-UD-Q4_K_XL.gguf}
-        https://huggingface.co/unsloth/Qwen3.8-27B-GGUF/resolve/main/${LLAMA_MODEL_FILE:-Qwen3.8-27B-UD-Q4_K_XL.gguf}
-
-  downloader-draft:
-    image: curlimages/curl:latest
-    profiles: ["tools"]
-    user: root
-    volumes:
-      - models:/models
-    entrypoint: ["sh", "-c"]
-    command:
-      - >
-        test -f /models/${LLAMA_DRAFT_MODEL_FILE:-Qwen3.8-27B-DFlash2-Q4_K_M.gguf} &&
-        echo "already downloaded, skipping" ||
-        curl -L --fail --create-dirs -o /models/${LLAMA_DRAFT_MODEL_FILE:-Qwen3.8-27B-DFlash2-Q4_K_M.gguf}
-        https://huggingface.co/z-lab/Qwen3.8-27B-DFlash2-GGUF/resolve/main/${LLAMA_DRAFT_MODEL_FILE:-Qwen3.8-27B-DFlash2-Q4_K_M.gguf}
+      - |
+        apk add --no-cache -q curl yq-go
+        yq -r '.models[] | (.file // "") + " " + (.url // "")' /models.yml | while read -r file url; do
+          if [ -z "$$url" ]; then echo "models.yml: entry '$$file' needs both file and url" >&2; exit 1; fi
+          if [ -f "/models/$$file" ]; then echo "$$file: already downloaded, skipping"; continue; fi
+          curl -L --fail -o "/models/$$file.part" "$$url"
+          mv "/models/$$file.part" "/models/$$file"
+        done
 
   # see docs/operations.md#speed-bench
   speed-bench: