Merge remote-tracking branch 'origin/master'

models.tsv

@@ -3,10 +3,15 @@
 # cpu_ok: yes = usable speed without a GPU (small dense or MoE with few active params).
 # rank: higher = better quality for coding; the recommender picks the highest rank that fits.
 qwen2.5-coder:1.5b	1.0	2.0	yes	10	Tiny; very fast, weak edits. For very small machines.
+granite-code:3b	2.0	3.0	yes	15	IBM, Apache-2.0 (fully permissive); a bit weaker than Qwen at this size.
 qwen2.5-coder:3b	1.9	3.0	yes	20	Small and fast; OK for simple edits.
+granite-code:8b	4.6	6.2	yes	27	IBM, Apache-2.0 (fully permissive); solid mid-size coder.
 qwen2.5-coder:7b	4.7	6.5	yes	30	Best all-round choice for laptops / CPU-only.
-deepseek-coder-v2:16b	8.9	11.5	yes	35	MoE (2.4B active): fast on CPU, needs ~12 GB RAM.
+granite-code:20b	12	15	no	33	IBM, Apache-2.0 (fully permissive); dense, wants a GPU (~15 GB).
+deepseek-coder-v2:16b	8.9	11.5	yes	35	MoE (Mixture of Experts, 2.4B active): fast on CPU, needs ~12 GB RAM.
 qwen2.5-coder:14b	9.0	11.5	no	40	Noticeably smarter than 7B; wants a GPU (~12 GB VRAM).
-gpt-oss:20b	14	17	yes	50	MoE reasoning model; needs ~17 GB RAM or VRAM.
+gpt-oss:20b	14	17	yes	50	MoE (Mixture of Experts) reasoning model; needs ~17 GB RAM or VRAM.
-qwen3-coder:30b	19	23	yes	60	MoE (3B active): strong coder, fast on CPU with 24+ GB RAM.
+granite-code:34b	19	23	no	55	IBM, Apache-2.0 (fully permissive); dense, needs a 24 GB GPU.
+devstral:24b	14	17	no	58	Mistral+All Hands, Apache-2.0; built for agentic multi-file edits, needs ~17 GB RAM or VRAM.
+qwen3-coder:30b	19	23	yes	60	MoE (Mixture of Experts, 3B active): strong coder, fast on CPU with 24+ GB RAM.
 qwen2.5-coder:32b	20	24	no	70	Top-quality dense coder; needs a 24 GB GPU.

run-ai-image.sh

@@ -10,6 +10,7 @@ cd "$(dirname "$0")"
 [ -f .ai-config ] || { echo "No .ai-config yet - run ./setup.sh first." >&2; exit 1; }
 # shellcheck disable=SC1091
 source .ai-config
+PORT=${AI_PORT:-$PORT}   # override for one run: AI_PORT=11500 ./run-ai-image.sh
 
 running() { [ "$(docker inspect -f '{{.State.Running}}' "$CONTAINER_NAME" 2>/dev/null)" = "true" ]; }
 exists()  { docker inspect "$CONTAINER_NAME" >/dev/null 2>&1; }
@@ -28,6 +29,12 @@ if running; then
   echo "Already running on http://127.0.0.1:$PORT"
 else
   exists && docker rm -f "$CONTAINER_NAME" >/dev/null
+  if (exec 3<>"/dev/tcp/127.0.0.1/$PORT") 2>/dev/null; then
+    echo "Port $PORT is already in use by something else (a host Ollama, another container?):" >&2
+    docker ps --filter "publish=$PORT" --format '  container {{.Names}}' >&2 || true
+    echo "Re-run ./setup.sh to pick a free port, or use: AI_PORT=<free port> ./run-ai-image.sh" >&2
+    exit 1
+  fi
   args=(-d --name "$CONTAINER_NAME" -p "127.0.0.1:$PORT:11434" --restart unless-stopped)
   [ "$USE_GPU" = "1" ] && args+=(--gpus all)
   docker run "${args[@]}" "$IMAGE_NAME" >/dev/null

setup.sh

@@ -4,24 +4,29 @@
 #   .ai-config   (settings used by build-ai-image.sh / run-ai-image.sh)
 #   RUN_AIDER.md (how to run aider against the container on this machine)
 #
-# Usage: ./setup.sh [--model <ollama-tag>] [--gpu|--no-gpu] [--yes]
+# Usage: ./setup.sh [--model <ollama-tag>] [--gpu|--no-gpu] [--port <n>] [--yes]
 set -euo pipefail
 cd "$(dirname "$0")"
+# Numeric formatting/parsing below assumes '.' as the decimal point (awk, sort -n).
+# A locale like de_DE (comma decimal separator) would corrupt those comparisons.
+export LC_ALL=C
 
-FORCE_MODEL=""; FORCE_GPU=""; ASSUME_YES=0
+FORCE_MODEL=""; FORCE_GPU=""; ASSUME_YES=0; FORCE_PORT=""
 while [ $# -gt 0 ]; do
   case "$1" in
     --model) FORCE_MODEL="${2:?--model needs a value}"; shift ;;
     --gpu) FORCE_GPU=1 ;;
     --no-gpu) FORCE_GPU=0 ;;
+    --port) FORCE_PORT="${2:?--port needs a value}"; shift ;;
     --yes|-y) ASSUME_YES=1 ;;
-    -h|--help) sed -n '2,8p' "$0" | sed 's/^# \?//'; exit 0 ;;
+    -h|--help) sed -n '2,9p' "$0" | sed 's/^# \?//'; exit 0 ;;
     *) echo "Unknown option: $1" >&2; exit 1 ;;
   esac
   shift
 done
 
-IMAGE_NAME="local-ai"; CONTAINER_NAME="local-ai"; PORT=11434
+IMAGE_NAME="local-ai"; CONTAINER_NAME="local-ai"; PORT=""
+port_busy() { (exec 3<>"/dev/tcp/127.0.0.1/$1") 2>/dev/null; }
 NOTES=()   # machine-specific remarks, echoed to the terminal and RUN_AIDER.md
 
 # Distro-specific commands to make an NVIDIA GPU usable from Docker.
@@ -127,9 +132,12 @@ echo
 
 # ------------------------------------------------ memory budget / context
 # What a model must fit into: VRAM when a GPU is used, else RAM minus headroom
-# for the OS, aider and the editor.
+# for the OS, aider and the editor. hard_budget/gpu_hard have almost no headroom -
+# a model only fitting there is "tight" (usable, but close other apps first).
 budget=$(awk -v r="$ram_gb" 'BEGIN {b=r-4; if (b<1) b=1; printf "%.1f", b}')
+hard_budget=$(awk -v r="$ram_gb" 'BEGIN {b=r-1; if (b<1) b=1; printf "%.1f", b}')
 gpu_budget=$(awk -v v="$vram_gb" 'BEGIN {printf "%.1f", v*0.9}')
+gpu_hard=$(awk -v v="$vram_gb" 'BEGIN {printf "%.1f", v*0.98}')
 
 if   awk -v b="$budget" 'BEGIN{exit !(b<6)}';  then CONTEXT=4096
 elif awk -v b="$budget" 'BEGIN{exit !(b>=40)}'; then CONTEXT=32768
@@ -143,10 +151,14 @@ for i in "${!rows[@]}"; do
   IFS=$'\t' read -r tag disk mem cpu_ok rank desc <<<"${rows[$i]}"
   tags[i]=$tag
   fits_ram=$(awk -v m="$mem" -v b="$budget" 'BEGIN{print (m<=b)}')
+  fits_hard_ram=$(awk -v m="$mem" -v b="$hard_budget" 'BEGIN{print (m<=b)}')
   fits_gpu=$(awk -v m="$mem" -v b="$gpu_budget" -v u="$gpu_usable" 'BEGIN{print (u && m<=b)}')
+  fits_hard_gpu=$(awk -v m="$mem" -v b="$gpu_hard" -v u="$gpu_usable" 'BEGIN{print (u && m<=b)}')
   if [ "$fits_gpu" = 1 ]; then status[i]="fits"; speed[i]="fast (GPU)"
+  elif [ "$fits_hard_gpu" = 1 ]; then status[i]="tight"; speed[i]="tight (GPU)"
   elif [ "$fits_ram" = 1 ] && [ "$cpu_ok" = yes ]; then status[i]="fits"; speed[i]="ok (CPU)"
   elif [ "$fits_ram" = 1 ]; then status[i]="slow"; speed[i]="slow (CPU)"
+  elif [ "$fits_hard_ram" = 1 ]; then status[i]="tight"; speed[i]="tight (CPU)"
   else status[i]="too big"; speed[i]="-"; fi
   [ "${status[$i]}" = fits ] && rec=$i     # sorted by rank, so last "fits" wins
 done
@@ -206,7 +218,10 @@ if [ -z "$FORCE_MODEL" ]; then
   [[ "$choice" =~ ^[0-9]+$ ]] && [ "$choice" -ge 1 ] && [ "$choice" -le "${#rows[@]}" ] || { echo "Invalid choice." >&2; exit 1; }
   sel=$((choice-1))
   MODEL=${tags[$sel]}
-  if [ "${status[$sel]}" = "too big" ] || [ "${status[$sel]}" = "slow" ]; then
+  if [ "${status[$sel]}" = "tight" ]; then
+    echo "Warning: $MODEL is 'tight' on this machine (fits, but leaves little headroom - close other apps first)."
+    if [ "$ASSUME_YES" != 1 ]; then read -r -p "Continue anyway? [y/N] " a; [[ "$a" =~ ^[Yy] ]] || exit 1; fi
+  elif [ "${status[$sel]}" = "too big" ] || [ "${status[$sel]}" = "slow" ]; then
     echo "Warning: $MODEL is '${status[$sel]}' on this machine (may swap, crawl, or crash)."
     if [ "$ASSUME_YES" != 1 ]; then read -r -p "Continue anyway? [y/N] " a; [[ "$a" =~ ^[Yy] ]] || exit 1; fi
   fi
@@ -219,6 +234,19 @@ if awk -v d="$sel_disk" -v f="$disk_gb" 'BEGIN{exit !(d*2>f)}'; then
   NOTES+=("Low disk space: ${disk_gb} GB free, the build needs roughly 2x the model size (${sel_disk} GB).")
 fi
 
+# ------------------------------------------------------------ host port
+# Default 11434 (Ollama's standard); if something else (e.g. a host Ollama)
+# already uses it, take the next free port.
+if [ -n "$FORCE_PORT" ]; then PORT=$FORCE_PORT
+else
+  for PORT in $(seq 11434 11534); do
+    # our own container from an earlier run doesn't count as busy
+    [ "$(docker port "$CONTAINER_NAME" 11434/tcp 2>/dev/null | head -1 | sed 's/.*://')" = "$PORT" ] && break
+    port_busy "$PORT" || break
+  done
+  [ "$PORT" != 11434 ] && NOTES+=("Port 11434 is already in use on this machine, so the AI container will use port $PORT.")
+fi
+
 # ------------------------------------------------------------------- output
 USE_GPU=$gpu_usable
 sed -e "s|@@MODEL@@|$MODEL|g" -e "s|@@CONTEXT@@|$CONTEXT|g" Dockerfile.template > Dockerfile