Add: CodeNeedle Benchmark. Optimize model handling.

scripts/benchmark-codeneedle-suite.sh

@@ -0,0 +1,393 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+PROJECT_DIR="$(cd "$SCRIPT_DIR/.." && pwd)"
+CODE_NEEDLE_REPO_URL="https://github.com/alexziskind1/codeneedle.git"
+
+usage() {
+  cat <<'EOF'
+Usage: ./scripts/benchmark-codeneedle-suite.sh [options]
+
+Vergleicht mehrere lokale Ollama-Modelle mit CodeNeedle gegen ein OpenAI-
+kompatibles Endpoint-Schema. Das Skript klont CodeNeedle zur Laufzeit unter
+.cache/benchmarks, baut das Upstream-Dockerfile mit Podman oder Docker und
+fuehrt die Standard-Corpora http_server und jquery gegen den lokalen Ollama-
+Server aus.
+
+Optionen:
+  --model <name>         Modellname in Ollama; mehrfach nutzbar
+                         (default: qwen3-coding:latest, qwen25-coding:latest,
+                         deepseek-coding:latest)
+  --corpus <name>        CodeNeedle-Corpus; mehrfach nutzbar
+                         (default: http_server, jquery)
+  --base-url <url>       OpenAI-kompatible Basis-URL ohne /v1-Suffix
+                         (default: http://127.0.0.1:11434)
+  --api-key <value>      API-Key fuer den Endpoint (default: not-needed)
+  --temperature <n>      Sampling-Temperatur (default: 0)
+  --max-tokens <n>       Antwortbudget je Query (default: 8000)
+  --timeout-sec <n>      Timeout je Query in Sekunden (default: 600)
+  --sample-k <n>         Anzahl der getesteten Funktionen je Corpus (default: 16)
+  --sample-seed <n>      Seed fuer die Stichprobe (default: 42)
+  --skip-preflight       Ueberspringt CodeNeedle-Preflight-Probe pro Lauf
+  --runtime-root <path>  Zielordner fuer temporaere Laufdaten (default: auto)
+  --results-root <path>  Zielordner fuer kuratierte Resultate (default: auto)
+  --artifact-root <path> Legacy-Alias; nutzt denselben Pfad fuer Runtime und Resultate
+  --repo-dir <path>      Ablageort fuer den Upstream-Clone (default: auto)
+  --image-tag <tag>      Name des lokal gebauten Runner-Images (default: ghostnet-codeneedle:latest)
+  --container-engine <e> podman oder docker (default: aus .env/.env.example oder auto)
+  --refresh-upstream     Upstream-Clone vor dem Lauf mit git pull aktualisieren
+  --rebuild-image        Image vor dem Lauf neu bauen
+  --keep-runtime         Runtime-Dateien nach dem Export nicht loeschen
+  -h, --help             Hilfe anzeigen
+EOF
+}
+
+need_cmd() {
+  if ! command -v "$1" >/dev/null 2>&1; then
+    echo "ERROR: Missing required command '$1'." >&2
+    exit 1
+  fi
+}
+
+read_env_var() {
+  local key="$1"
+  local file line
+
+  for file in "$PROJECT_DIR/.env" "$PROJECT_DIR/.env.example"; do
+    if [ ! -f "$file" ]; then
+      continue
+    fi
+
+    line="$(grep -E "^${key}=" "$file" | tail -n 1 || true)"
+    if [ -n "$line" ]; then
+      printf '%s\n' "${line#*=}"
+      return 0
+    fi
+  done
+
+  return 1
+}
+
+slugify() {
+  printf '%s' "$1" | tr '/:@ ' '----' | tr -cd '[:alnum:]_.-'
+}
+
+MODELS=(
+  "qwen3-coding:latest"
+  "qwen25-coding:latest"
+  "deepseek-coding:latest"
+)
+CORPORA=(
+  "http_server"
+  "jquery"
+)
+BASE_URL="http://127.0.0.1:11434"
+API_KEY="not-needed"
+TEMPERATURE="0"
+MAX_TOKENS=8000
+TIMEOUT_SEC=600
+SAMPLE_K=16
+SAMPLE_SEED=42
+SKIP_PREFLIGHT=0
+RUNTIME_ROOT=""
+RESULTS_ROOT=""
+LEGACY_ARTIFACT_ROOT=""
+REPO_DIR=""
+IMAGE_TAG="ghostnet-codeneedle:latest"
+CONTAINER_ENGINE="${CONTAINER_ENGINE:-}"
+REFRESH_UPSTREAM=0
+REBUILD_IMAGE=0
+KEEP_RUNTIME=0
+
+while [ $# -gt 0 ]; do
+  case "$1" in
+    --model)
+      if [ "${MODELS[0]:-}" = "qwen3-coding:latest" ] && [ "${#MODELS[@]}" -eq 3 ]; then
+        MODELS=()
+      fi
+      MODELS+=("$2")
+      shift 2
+      ;;
+    --corpus)
+      if [ "${CORPORA[0]:-}" = "http_server" ] && [ "${#CORPORA[@]}" -eq 2 ]; then
+        CORPORA=()
+      fi
+      CORPORA+=("$2")
+      shift 2
+      ;;
+    --base-url)
+      BASE_URL="$2"
+      shift 2
+      ;;
+    --api-key)
+      API_KEY="$2"
+      shift 2
+      ;;
+    --temperature)
+      TEMPERATURE="$2"
+      shift 2
+      ;;
+    --max-tokens)
+      MAX_TOKENS="$2"
+      shift 2
+      ;;
+    --timeout-sec)
+      TIMEOUT_SEC="$2"
+      shift 2
+      ;;
+    --sample-k)
+      SAMPLE_K="$2"
+      shift 2
+      ;;
+    --sample-seed)
+      SAMPLE_SEED="$2"
+      shift 2
+      ;;
+    --skip-preflight)
+      SKIP_PREFLIGHT=1
+      shift
+      ;;
+    --runtime-root)
+      RUNTIME_ROOT="$2"
+      shift 2
+      ;;
+    --results-root)
+      RESULTS_ROOT="$2"
+      shift 2
+      ;;
+    --artifact-root)
+      LEGACY_ARTIFACT_ROOT="$2"
+      shift 2
+      ;;
+    --repo-dir)
+      REPO_DIR="$2"
+      shift 2
+      ;;
+    --image-tag)
+      IMAGE_TAG="$2"
+      shift 2
+      ;;
+    --container-engine)
+      CONTAINER_ENGINE="$2"
+      shift 2
+      ;;
+    --refresh-upstream)
+      REFRESH_UPSTREAM=1
+      shift
+      ;;
+    --rebuild-image)
+      REBUILD_IMAGE=1
+      shift
+      ;;
+    --keep-runtime)
+      KEEP_RUNTIME=1
+      shift
+      ;;
+    -h|--help)
+      usage
+      exit 0
+      ;;
+    *)
+      echo "ERROR: Unknown option '$1'." >&2
+      usage >&2
+      exit 1
+      ;;
+  esac
+done
+
+need_cmd git
+need_cmd jq
+
+if [ -z "$CONTAINER_ENGINE" ]; then
+  CONTAINER_ENGINE="$(read_env_var CONTAINER_ENGINE || true)"
+fi
+
+if [ -z "$CONTAINER_ENGINE" ]; then
+  if command -v podman >/dev/null 2>&1; then
+    CONTAINER_ENGINE="podman"
+  elif command -v docker >/dev/null 2>&1; then
+    CONTAINER_ENGINE="docker"
+  else
+    echo "ERROR: Neither podman nor docker is available." >&2
+    exit 1
+  fi
+fi
+
+case "$CONTAINER_ENGINE" in
+  podman)
+    ENGINE_CMD=(podman)
+    MOUNT_SUFFIX=':Z'
+    ;;
+  docker)
+    ENGINE_CMD=(docker)
+    MOUNT_SUFFIX=''
+    ;;
+  *)
+    echo "ERROR: Invalid container engine '$CONTAINER_ENGINE'. Use 'podman' or 'docker'." >&2
+    exit 1
+    ;;
+esac
+
+need_cmd "${ENGINE_CMD[0]}"
+
+RUN_ID="codeneedle-suite-$(date +%Y%m%d-%H%M%S)"
+
+if [ -n "$LEGACY_ARTIFACT_ROOT" ]; then
+  RUNTIME_ROOT="$LEGACY_ARTIFACT_ROOT"
+  if [ -z "$RESULTS_ROOT" ]; then
+    RESULTS_ROOT="$LEGACY_ARTIFACT_ROOT"
+    KEEP_RUNTIME=1
+  fi
+fi
+
+if [ -z "$RUNTIME_ROOT" ]; then
+  RUNTIME_ROOT="$PROJECT_DIR/.cache/benchmarks/$RUN_ID"
+fi
+
+if [ -z "$RESULTS_ROOT" ]; then
+  RESULTS_ROOT="$PROJECT_DIR/docs/benchmarks/codeneedle/$RUN_ID"
+fi
+
+if [ -z "$REPO_DIR" ]; then
+  REPO_DIR="$PROJECT_DIR/.cache/benchmarks/codeneedle/upstream"
+fi
+
+mkdir -p "$RUNTIME_ROOT" "$RESULTS_ROOT"
+
+if [ ! -d "$REPO_DIR/.git" ]; then
+  mkdir -p "$(dirname "$REPO_DIR")"
+  git clone --depth 1 "$CODE_NEEDLE_REPO_URL" "$REPO_DIR"
+elif [ "$REFRESH_UPSTREAM" -eq 1 ]; then
+  git -C "$REPO_DIR" pull --ff-only
+fi
+
+UPSTREAM_REF="$(git -C "$REPO_DIR" rev-parse HEAD)"
+
+if [ "$REBUILD_IMAGE" -eq 1 ] || ! "${ENGINE_CMD[@]}" image inspect "$IMAGE_TAG" >/dev/null 2>&1; then
+  "${ENGINE_CMD[@]}" build -t "$IMAGE_TAG" -f "$REPO_DIR/Dockerfile" "$REPO_DIR"
+fi
+
+SUMMARY_TABLE="$RESULTS_ROOT/summary.tsv"
+RUN_METADATA_FILE="$RESULTS_ROOT/run-metadata.txt"
+printf 'corpus\tmodel\trun_rc\tpassed\ttotal\terrored\tprimary_matched\tprimary_total\thallucinated\tbonus\n' > "$SUMMARY_TABLE"
+
+cat > "$RUN_METADATA_FILE" <<EOF
+run_id=$RUN_ID
+container_engine=$CONTAINER_ENGINE
+image_tag=$IMAGE_TAG
+upstream_repo=$CODE_NEEDLE_REPO_URL
+upstream_ref=$UPSTREAM_REF
+base_url=$BASE_URL
+temperature=$TEMPERATURE
+max_tokens=$MAX_TOKENS
+timeout_sec=$TIMEOUT_SEC
+sample_k=$SAMPLE_K
+sample_seed=$SAMPLE_SEED
+skip_preflight=$SKIP_PREFLIGHT
+repo_dir=$REPO_DIR
+runtime_root=$RUNTIME_ROOT
+results_root=$RESULTS_ROOT
+EOF
+
+echo "CodeNeedle-Repo: $REPO_DIR @ $UPSTREAM_REF"
+echo "Container-Engine: $CONTAINER_ENGINE"
+echo "Image: $IMAGE_TAG"
+echo "Base URL: $BASE_URL"
+echo "Runtime-Wurzel: $RUNTIME_ROOT"
+echo "Kuratierte Resultate: $RESULTS_ROOT"
+echo
+
+for corpus in "${CORPORA[@]}"; do
+  for model in "${MODELS[@]}"; do
+    corpus_slug="$(slugify "$corpus")"
+    model_slug="$(slugify "$model")"
+    runtime_dir="$RUNTIME_ROOT/$corpus_slug/$model_slug"
+    results_dir="$RESULTS_ROOT/$corpus_slug/$model_slug"
+    dump_file="$runtime_dir/results.json"
+    stdout_file="$runtime_dir/stdout.log"
+    stderr_file="$runtime_dir/stderr.log"
+    run_cmd=(
+      "${ENGINE_CMD[@]}" run --rm --network host
+      -v "$REPO_DIR:/app$MOUNT_SUFFIX"
+      -v "$runtime_dir:/runtime$MOUNT_SUFFIX"
+      -w /app
+      "$IMAGE_TAG"
+      python bench.py run
+      --corpus "$corpus"
+      --model "$model"
+      --base-url "$BASE_URL"
+      --api-key "$API_KEY"
+      --temperature "$TEMPERATURE"
+      --max-tokens "$MAX_TOKENS"
+      --timeout "$TIMEOUT_SEC"
+      -k "$SAMPLE_K"
+      --seed "$SAMPLE_SEED"
+      --dump /runtime/results.json
+    )
+
+    if [ "$SKIP_PREFLIGHT" -eq 1 ]; then
+      run_cmd+=(--skip-preflight)
+    fi
+
+    mkdir -p "$runtime_dir" "$results_dir"
+
+    echo "=== CodeNeedle fuer $model auf $corpus ==="
+    if "${run_cmd[@]}" >"$stdout_file" 2>"$stderr_file"; then
+      run_rc=0
+    else
+      run_rc=$?
+    fi
+
+    cp "$stdout_file" "$results_dir/stdout.log"
+    cp "$stderr_file" "$results_dir/stderr.log"
+
+    passed=""
+    total=""
+    errored=""
+    primary_matched=""
+    primary_total=""
+    hallucinated=""
+    bonus=""
+
+    if [ -f "$dump_file" ]; then
+      cp "$dump_file" "$results_dir/results.json"
+      passed="$(jq '[.results[] | select(.passed == true and (.error == null or .error == ""))] | length' "$dump_file")"
+      total="$(jq '.results | length' "$dump_file")"
+      errored="$(jq '[.results[] | select(.error != null and .error != "")] | length' "$dump_file")"
+      primary_matched="$(jq '[.results[].primary_matched] | add // 0' "$dump_file")"
+      primary_total="$(jq '[.results[].primary_total] | add // 0' "$dump_file")"
+      hallucinated="$(jq '[.results[].hallucinated] | add // 0' "$dump_file")"
+      bonus="$(jq '[.results[].bonus_matched] | add // 0' "$dump_file")"
+    fi
+
+    cat > "$results_dir/summary.txt" <<EOF
+corpus=$corpus
+model=$model
+run_rc=$run_rc
+passed=$passed
+total=$total
+errored=$errored
+primary_matched=$primary_matched
+primary_total=$primary_total
+hallucinated=$hallucinated
+bonus=$bonus
+EOF
+
+    printf '%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\n' \
+      "$corpus" "$model" "$run_rc" "$passed" "$total" "$errored" \
+      "$primary_matched" "$primary_total" "$hallucinated" "$bonus" >> "$SUMMARY_TABLE"
+
+    if [ "$KEEP_RUNTIME" -eq 0 ] && [ "$runtime_dir" != "$results_dir" ]; then
+      rm -rf "$runtime_dir"
+    fi
+  done
+done
+
+echo
+echo "CodeNeedle-Vergleich gespeichert unter: $RESULTS_ROOT"
+if command -v column >/dev/null 2>&1; then
+  column -ts $'\t' "$SUMMARY_TABLE"
+else
+  cat "$SUMMARY_TABLE"
+fi

scripts/benchmark-model-suite.sh

@@ -5,6 +5,9 @@ set -euo pipefail
 PROJECT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
 cd "$PROJECT_DIR"
 
+# Source report generator
+source "$PROJECT_DIR/scripts/lib/report-generator.sh" 2>/dev/null || true
+
 usage() {
   cat <<'EOF'
 Usage: ./scripts/benchmark-model-suite.sh [options]
@@ -14,8 +17,11 @@ und schreibt Artefakte plus eine Vergleichszusammenfassung.
 
 Optionen:
   --lines <n>           Erwartete Zeilenanzahl LINE_1..LINE_n (default: 140)
-  --timeout-sec <n>     Timeout je Lauf in Sekunden (default: 300)
-  --artifact-root <p>   Zielordner fuer alle Benchmark-Artefakte (default: auto)
+  --timeout-sec <n>     Timeout je Lauf in Sekunden (default: 600)
+  --runtime-root <p>    Zielordner fuer temporaere Laufdaten (default: auto)
+  --results-root <p>    Zielordner fuer kuratierte Resultate (default: auto)
+  --artifact-root <p>   Legacy-Alias; nutzt denselben Pfad fuer Runtime und Resultate
+  --keep-runtime        Runtime-Dateien der Einzelruns nicht loeschen
   --session-prefix <s>  Prefix fuer Session-Keys (default: suite:<timestamp>)
   -h, --help            Hilfe anzeigen
 EOF
@@ -46,8 +52,11 @@ extract_metric() {
 }
 
 EXPECTED_LINES=140
-TIMEOUT_SEC=300
-ARTIFACT_ROOT=""
+TIMEOUT_SEC=600
+RUNTIME_ROOT=""
+RESULTS_ROOT=""
+LEGACY_ARTIFACT_ROOT=""
+KEEP_RUNTIME=0
 SESSION_PREFIX="suite:$(date +%Y%m%d-%H%M%S)"
 
 while [ "$#" -gt 0 ]; do
@@ -60,10 +69,22 @@ while [ "$#" -gt 0 ]; do
       TIMEOUT_SEC="$2"
       shift 2
       ;;
-    --artifact-root)
-      ARTIFACT_ROOT="$2"
+    --runtime-root)
+      RUNTIME_ROOT="$2"
       shift 2
       ;;
+    --results-root)
+      RESULTS_ROOT="$2"
+      shift 2
+      ;;
+    --artifact-root)
+      LEGACY_ARTIFACT_ROOT="$2"
+      shift 2
+      ;;
+    --keep-runtime)
+      KEEP_RUNTIME=1
+      shift
+      ;;
     --session-prefix)
       SESSION_PREFIX="$2"
       shift 2
@@ -80,11 +101,25 @@ while [ "$#" -gt 0 ]; do
   esac
 done
 
-if [ -z "$ARTIFACT_ROOT" ]; then
-  ARTIFACT_ROOT="$PROJECT_DIR/storage/workspace/benchmarks/model-suite-$(date +%Y%m%d-%H%M%S)"
+RUN_ID="model-suite-$(date +%Y%m%d-%H%M%S)"
+
+if [ -n "$LEGACY_ARTIFACT_ROOT" ]; then
+  RUNTIME_ROOT="$LEGACY_ARTIFACT_ROOT"
+  if [ -z "$RESULTS_ROOT" ]; then
+    RESULTS_ROOT="$LEGACY_ARTIFACT_ROOT"
+    KEEP_RUNTIME=1
+  fi
 fi
 
-mkdir -p "$ARTIFACT_ROOT"
+if [ -z "$RUNTIME_ROOT" ]; then
+  RUNTIME_ROOT="$PROJECT_DIR/.cache/benchmarks/$RUN_ID"
+fi
+
+if [ -z "$RESULTS_ROOT" ]; then
+  RESULTS_ROOT="$PROJECT_DIR/docs/benchmarks/existing-suite/$RUN_ID"
+fi
+
+mkdir -p "$RUNTIME_ROOT" "$RESULTS_ROOT"
 
 MODELS=(
   "ollama/qwen3-coding:latest"
@@ -92,27 +127,36 @@ MODELS=(
   "ollama/deepseek-coding:latest"
 )
 
-SUMMARY_TABLE="$ARTIFACT_ROOT/summary.tsv"
+SUMMARY_TABLE="$RESULTS_ROOT/summary.tsv"
 printf 'model\tbenchmark_rc\tvalidation\trequest_exit\twall_ms\tprovider_tps\tend_to_end_tps\tload_sec\tkv_tokens\n' > "$SUMMARY_TABLE"
 
 for model in "${MODELS[@]}"; do
   slug="$(slugify_model "$model")"
-  run_dir="$ARTIFACT_ROOT/$slug"
+  runtime_dir="$RUNTIME_ROOT/$slug"
+  results_dir="$RESULTS_ROOT/$slug"
   session_key="$SESSION_PREFIX:$slug"
+  run_args=(
+    --model "$model"
+    --lines "$EXPECTED_LINES"
+    --timeout-sec "$TIMEOUT_SEC"
+    --session-key "$session_key"
+    --runtime-dir "$runtime_dir"
+    --results-dir "$results_dir"
+    --no-start
+  )
+
+  if [ "$KEEP_RUNTIME" -eq 1 ]; then
+    run_args+=(--keep-runtime)
+  fi
 
   echo "=== Benchmark fuer $model ==="
-  benchmark_rc=0
-  if ! ./scripts/benchmark-stack.sh \
-    --model "$model" \
-    --lines "$EXPECTED_LINES" \
-    --timeout-sec "$TIMEOUT_SEC" \
-    --session-key "$session_key" \
-    --artifact-dir "$run_dir" \
-    --no-start; then
+  if ./scripts/benchmark-stack.sh "${run_args[@]}"; then
+    benchmark_rc=0
+  else
     benchmark_rc=$?
   fi
 
-  summary_file="$run_dir/summary.txt"
+  summary_file="$results_dir/summary.txt"
 
   validation="$(extract_value 'Validation' "$summary_file")"
   request_exit="$(extract_value 'Request exit code' "$summary_file")"
@@ -128,5 +172,14 @@ for model in "${MODELS[@]}"; do
 done
 
 echo
-echo "Vergleich gespeichert unter: $ARTIFACT_ROOT"
-column -ts $'\t' "$SUMMARY_TABLE"
+echo "Runtime-Wurzel: $RUNTIME_ROOT"
+echo "Kuratierte Resultate: $RESULTS_ROOT"
+column -ts $'\t' "$SUMMARY_TABLE"
+
+# Generate suite comparison report
+if [ -f "$SUMMARY_TABLE" ]; then
+  echo
+  echo "📊 Generating suite comparison report..."
+  generate_suite_comparison_report "$SUMMARY_TABLE" "$RESULTS_ROOT" 2>/dev/null || true
+  echo "✅ Reports generated in: $RESULTS_ROOT"
+fi

scripts/benchmark-stack.sh

@@ -5,6 +5,9 @@ set -euo pipefail
 PROJECT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
 cd "$PROJECT_DIR"
 
+# Source report generator
+source "$PROJECT_DIR/scripts/lib/report-generator.sh" 2>/dev/null || true
+
 RED='\033[0;31m'
 GREEN='\033[0;32m'
 YELLOW='\033[1;33m'
@@ -27,6 +30,37 @@ need_cmd() {
   command -v "$1" >/dev/null 2>&1 || fail "Benoetigtes Kommando fehlt: $1"
 }
 
+read_env_var() {
+  local key="$1"
+  local env_file="$PROJECT_DIR/.env"
+  local line=""
+
+  if [ -f "$env_file" ]; then
+    line="$(grep -E "^${key}=" "$env_file" | tail -n 1 || true)"
+  fi
+
+  if [ -z "$line" ] && [ -f "$PROJECT_DIR/.env.example" ]; then
+    line="$(grep -E "^${key}=" "$PROJECT_DIR/.env.example" | tail -n 1 || true)"
+  fi
+
+  if [ -n "$line" ]; then
+    printf '%s' "${line#*=}"
+  fi
+}
+
+resolve_abs_path() {
+  local raw_path="$1"
+  if [[ "$raw_path" = /* ]]; then
+    printf '%s' "$raw_path"
+    return
+  fi
+  if command -v realpath >/dev/null 2>&1; then
+    realpath -m "$PROJECT_DIR/$raw_path"
+    return
+  fi
+  (cd "$PROJECT_DIR" && printf '%s/%s\n' "$PWD" "${raw_path#./}")
+}
+
 usage() {
   cat <<'EOF'
 Usage: ./scripts/benchmark-stack.sh [options]
@@ -37,9 +71,12 @@ validiert den Output und zeigt Metriken (Laufzeit, Token, KV-/VRAM-Metriken).
 Optionen:
   --model <name>          OpenClaw-Modell (default: ollama/qwen3-coding:latest)
   --lines <n>             Erwartete Zeilenanzahl LINE_1..LINE_n (default: 120)
-  --timeout-sec <n>       Timeout fuer den Agent-Call in Sekunden (default: 480)
+  --timeout-sec <n>       Timeout fuer den Agent-Call in Sekunden (default: 600)
   --session-key <key>     Session-Key fuer den Lauf (default: auto)
-  --artifact-dir <path>   Zielverzeichnis fuer Ergebnisdateien (default: auto)
+  --runtime-dir <path>    Zielverzeichnis fuer temporaere Laufdaten (default: auto)
+  --results-dir <path>    Zielverzeichnis fuer kuratierte Resultate (default: auto)
+  --artifact-dir <path>   Legacy-Alias; nutzt denselben Pfad fuer Runtime und Resultate
+  --keep-runtime          Runtime-Dateien nach dem Export nicht loeschen
   --no-start              Stack nicht starten, nur vorhandenen Stack nutzen
   --no-reload             Modell vor Lauf nicht mit 'ollama stop' entladen
   -h, --help              Hilfe anzeigen
@@ -132,13 +169,81 @@ extract_unquoted_metric() {
   fi
 }
 
+resolve_workspace_media_path() {
+  local media_path="$1"
+  local normalized="$media_path"
+
+  normalized="${normalized#/workspace/}"
+  normalized="${normalized#/home/node/.openclaw/workspace/}"
+
+  if [ -z "$normalized" ] || [ "$normalized" = "$media_path" -a [[ "$media_path" = /* ]] ]; then
+    return 1
+  fi
+
+  printf '%s/%s\n' "$HOST_WORKSPACE_ABS" "$normalized"
+}
+
+extract_tool_call_text() {
+  local raw_text="$1"
+  local extracted
+
+  extracted="$(printf '%s\n' "$raw_text" | sed '/^```json$/d; /^```$/d; /^```$/d' | jq -rs '
+    map(select(type == "object" and (.name == "write" or .name == "edit"))) as $calls
+    | if ($calls | length) == 0 then ""
+      else
+        reduce $calls[] as $call ({content: ""};
+          if $call.name == "write" then
+            .content = ($call.arguments.content // .content)
+          elif $call.name == "edit" then
+            .content = (
+              if (($call.arguments.edits // []) | length) > 0 then
+                ($call.arguments.edits[-1].newText // .content)
+              else
+                .content
+              end
+            )
+          else
+            .
+          end
+        )
+        | .content
+      end
+  ' 2>/dev/null || true)"
+
+  if [ -n "$extracted" ]; then
+    printf '%s' "$extracted"
+    return 0
+  fi
+
+  return 1
+}
+
+extract_media_payload_text() {
+  local media_path=""
+  local host_path=""
+
+  while IFS= read -r media_path; do
+    [ -n "$media_path" ] || continue
+    host_path="$(resolve_workspace_media_path "$media_path" || true)"
+    if [ -n "$host_path" ] && [ -f "$host_path" ]; then
+      cat "$host_path"
+      return 0
+    fi
+  done < <(jq -r '.result.payloads[]? | .mediaUrl?, (.mediaUrls[]?)' "$JSON_OUT_FILE" 2>/dev/null | awk 'NF && !seen[$0]++')
+
+  return 1
+}
+
 MODEL="ollama/qwen3-coding:latest"
 EXPECTED_LINES=120
-TIMEOUT_SEC=480
+TIMEOUT_SEC=600
 SESSION_KEY=""
-ARTIFACT_DIR=""
+RUNTIME_DIR=""
+RESULTS_DIR=""
+LEGACY_ARTIFACT_DIR=""
 START_STACK=1
 FORCE_RELOAD=1
+KEEP_RUNTIME=0
 
 while [ "$#" -gt 0 ]; do
   case "$1" in
@@ -158,10 +263,22 @@ while [ "$#" -gt 0 ]; do
       SESSION_KEY="$2"
       shift 2
       ;;
-    --artifact-dir)
-      ARTIFACT_DIR="$2"
+    --runtime-dir)
+      RUNTIME_DIR="$2"
       shift 2
       ;;
+    --results-dir)
+      RESULTS_DIR="$2"
+      shift 2
+      ;;
+    --artifact-dir)
+      LEGACY_ARTIFACT_DIR="$2"
+      shift 2
+      ;;
+    --keep-runtime)
+      KEEP_RUNTIME=1
+      shift
+      ;;
     --no-start)
       START_STACK=0
       shift
@@ -195,19 +312,44 @@ need_cmd sed
 need_cmd awk
 need_cmd timeout
 
-if [ -z "$ARTIFACT_DIR" ]; then
-  TS="$(date +%Y%m%d-%H%M%S)"
-  ARTIFACT_DIR="$PROJECT_DIR/storage/workspace/benchmarks/$TS"
-fi
-mkdir -p "$ARTIFACT_DIR"
+RUN_ID="$(date +%Y%m%d-%H%M%S)"
+HOST_WORKSPACE_RAW="$(read_env_var HOST_WORKSPACE_PATH)"
+HOST_WORKSPACE_RAW="${HOST_WORKSPACE_RAW:-./storage/workspace}"
+HOST_WORKSPACE_ABS="$(resolve_abs_path "$HOST_WORKSPACE_RAW")"
+BENCH_OUTPUT_FILENAME="benchmark-output-${RUN_ID}.txt"
 
-JSON_OUT_FILE="$ARTIFACT_DIR/agent-result.json"
-ASSISTANT_TEXT_FILE="$ARTIFACT_DIR/assistant-output.txt"
-OLLAMA_LOG_FILE="$ARTIFACT_DIR/ollama-since.log"
-STATS_BEFORE_FILE="$ARTIFACT_DIR/container-stats-before.txt"
-STATS_AFTER_FILE="$ARTIFACT_DIR/container-stats-after.txt"
-REQUEST_ERR_FILE="$ARTIFACT_DIR/request-stderr.log"
-SUMMARY_FILE="$ARTIFACT_DIR/summary.txt"
+if [ -n "$LEGACY_ARTIFACT_DIR" ]; then
+  RUNTIME_DIR="$LEGACY_ARTIFACT_DIR"
+  if [ -z "$RESULTS_DIR" ]; then
+    RESULTS_DIR="$LEGACY_ARTIFACT_DIR"
+    KEEP_RUNTIME=1
+  fi
+fi
+
+if [ -z "$RUNTIME_DIR" ]; then
+  RUNTIME_DIR="$PROJECT_DIR/.cache/benchmarks/existing-suite/runs/$RUN_ID"
+fi
+
+if [ -z "$RESULTS_DIR" ]; then
+  RESULTS_DIR="$PROJECT_DIR/docs/benchmarks/existing-suite/$RUN_ID"
+fi
+
+mkdir -p "$RUNTIME_DIR" "$RESULTS_DIR"
+
+JSON_OUT_FILE="$RUNTIME_DIR/agent-result.json"
+ASSISTANT_TEXT_FILE="$RUNTIME_DIR/assistant-output.txt"
+OLLAMA_LOG_FILE="$RUNTIME_DIR/ollama-since.log"
+STATS_BEFORE_FILE="$RUNTIME_DIR/container-stats-before.txt"
+STATS_AFTER_FILE="$RUNTIME_DIR/container-stats-after.txt"
+REQUEST_ERR_FILE="$RUNTIME_DIR/request-stderr.log"
+SUMMARY_FILE="$RUNTIME_DIR/summary.txt"
+EXPORTED_SUMMARY_FILE="$RESULTS_DIR/summary.txt"
+EXPORTED_ASSISTANT_FILE="$RESULTS_DIR/assistant-output.txt"
+EXPORTED_JSON_FILE="$RESULTS_DIR/agent-result.json"
+EXPORTED_OLLAMA_LOG_FILE="$RESULTS_DIR/ollama-since.log"
+EXPORTED_STATS_BEFORE_FILE="$RESULTS_DIR/container-stats-before.txt"
+EXPORTED_STATS_AFTER_FILE="$RESULTS_DIR/container-stats-after.txt"
+EXPORTED_REQUEST_ERR_FILE="$RESULTS_DIR/request-stderr.log"
 
 if [ -z "$SESSION_KEY" ]; then
   SESSION_KEY="agent:main:benchmark:$(date +%s)"
@@ -221,7 +363,8 @@ echo "Model: $MODEL"
 echo "Session key: $SESSION_KEY"
 echo "Erwartete Zeilen: $EXPECTED_LINES"
 echo "Timeout: ${TIMEOUT_SEC}s"
-echo "Artefakte: $ARTIFACT_DIR"
+echo "Runtime-Dateien: $RUNTIME_DIR"
+echo "Kuratierte Resultate: $RESULTS_DIR"
 
 if [ "$START_STACK" -eq 1 ]; then
   echo
@@ -247,7 +390,7 @@ else
 fi
 
 echo "[4/6] Fuehre Benchmark-Anfrage aus ..."
-PROMPT="Gib exakt ${EXPECTED_LINES} Zeilen aus. Jede Zeile muss exakt den Text LINE_<n> haben, mit aufsteigender Nummerierung von 1 bis ${EXPECTED_LINES}. Kein weiterer Text."
+PROMPT="Gib exakt ${EXPECTED_LINES} Zeilen aus. Jede Zeile muss exakt den Text LINE_<n> haben, mit aufsteigender Nummerierung von 1 bis ${EXPECTED_LINES}. Kein weiterer Text. Nutze keine Tools, keine Dateien, keine Anhaenge und kein JSON. Antworte direkt als reiner Nachrichtentext. Falls du trotzdem Tools benutzt, schreibe exakt diese Zeilen in die Datei ${BENCH_OUTPUT_FILENAME} im Workspace und sonst nirgendwo hin."
 SINCE_UTC="$(date -u +%Y-%m-%dT%H:%M:%SZ)"
 
 podman stats --no-stream --format 'table {{.Name}}\t{{.CPUPerc}}\t{{.MemUsage}}\t{{.MemPerc}}' ollama openclaw > "$STATS_BEFORE_FILE" 2>&1 || true
@@ -257,6 +400,7 @@ REQUEST_RC=0
 if ! timeout "${TIMEOUT_SEC}s" podman exec openclaw openclaw agent \
   --session-key "$SESSION_KEY" \
   --model "$MODEL" \
+  --thinking off \
   --message "$PROMPT" \
   --json > "$JSON_OUT_FILE" 2> "$REQUEST_ERR_FILE"; then
   REQUEST_RC=$?
@@ -290,8 +434,19 @@ fi
 
 echo "[5/6] Validiere Antwortformat ..."
 ASSISTANT_TEXT=""
+RAW_ASSISTANT_TEXT=""
 if [ "$HAS_VALID_JSON" -eq 1 ]; then
-  ASSISTANT_TEXT="$(jq -r '.result.payloads[0].text // ""' "$JSON_OUT_FILE")"
+  RAW_ASSISTANT_TEXT="$(jq -r '[.result.payloads[]?.text // empty] | join("\n")' "$JSON_OUT_FILE")"
+  ASSISTANT_TEXT="$RAW_ASSISTANT_TEXT"
+  if [ -n "$RAW_ASSISTANT_TEXT" ]; then
+    TOOL_CALL_TEXT="$(extract_tool_call_text "$RAW_ASSISTANT_TEXT" || true)"
+    if [ -n "$TOOL_CALL_TEXT" ]; then
+      ASSISTANT_TEXT="$TOOL_CALL_TEXT"
+    fi
+  fi
+  if [ -z "$ASSISTANT_TEXT" ]; then
+    ASSISTANT_TEXT="$(extract_media_payload_text || true)"
+  fi
 fi
 printf '%s' "$ASSISTANT_TEXT" > "$ASSISTANT_TEXT_FILE"
 
@@ -426,12 +581,12 @@ fi
   echo "- journal_gpu_related_hits_since_start: $JOURNAL_HITS"
   echo
   echo "Artefakte"
-  echo "- agent_json: $JSON_OUT_FILE"
-  echo "- assistant_text: $ASSISTANT_TEXT_FILE"
-  echo "- ollama_log_since_start: $OLLAMA_LOG_FILE"
-  echo "- stats_before: $STATS_BEFORE_FILE"
-  echo "- stats_after: $STATS_AFTER_FILE"
-  echo "- request_stderr: $REQUEST_ERR_FILE"
+  echo "- agent_json: $EXPORTED_JSON_FILE"
+  echo "- assistant_text: $EXPORTED_ASSISTANT_FILE"
+  echo "- ollama_log_since_start: $EXPORTED_OLLAMA_LOG_FILE"
+  echo "- stats_before: $EXPORTED_STATS_BEFORE_FILE"
+  echo "- stats_after: $EXPORTED_STATS_AFTER_FILE"
+  echo "- request_stderr: $EXPORTED_REQUEST_ERR_FILE"
 } | tee "$SUMMARY_FILE"
 
 echo
@@ -441,6 +596,30 @@ echo
 echo "Container-Stats nach Lauf:"
 cat "$STATS_AFTER_FILE"
 
+cp "$SUMMARY_FILE" "$EXPORTED_SUMMARY_FILE"
+cp "$ASSISTANT_TEXT_FILE" "$EXPORTED_ASSISTANT_FILE"
+cp "$JSON_OUT_FILE" "$EXPORTED_JSON_FILE"
+cp "$OLLAMA_LOG_FILE" "$EXPORTED_OLLAMA_LOG_FILE"
+cp "$STATS_BEFORE_FILE" "$EXPORTED_STATS_BEFORE_FILE"
+cp "$STATS_AFTER_FILE" "$EXPORTED_STATS_AFTER_FILE"
+
+if [ -s "$REQUEST_ERR_FILE" ]; then
+  cp "$REQUEST_ERR_FILE" "$EXPORTED_REQUEST_ERR_FILE"
+fi
+
+if [ "$KEEP_RUNTIME" -eq 0 ] && [ "$RUNTIME_DIR" != "$RESULTS_DIR" ]; then
+  rm -rf "$RUNTIME_DIR"
+fi
+
+# Generate professional reports
+if [ -f "$EXPORTED_SUMMARY_FILE" ]; then
+  ok "Generating HTML report..."
+  generate_html_report "$MODEL_NAME" "$RESULTS_DIR" "$EXPORTED_SUMMARY_FILE" 2>/dev/null || true
+  
+  ok "Generating Markdown summary..."
+  generate_markdown_summary "$MODEL_NAME" "$RESULTS_DIR" "$EXPORTED_SUMMARY_FILE" 2>/dev/null || true
+fi
+
 if [ "$REQUEST_RC" -eq 0 ] && [ "$VALIDATION_OK" -eq 1 ]; then
   ok "Benchmark erfolgreich abgeschlossen"
   exit 0