chore: fix autoresearch benchmark model id

autoresearch.sh

@@ -6,6 +6,8 @@ ROOT="$SCRIPT_DIR"
 PORT="${LOCALLLM_BENCH_PORT:-18080}"
 HOST="127.0.0.1:${PORT}"
 MODEL_PATH="${LOCALLLM_MODEL:-$ROOT/models/Qwen3.5-4B-Abliterated-Claude-4.6-Opus-Reasoning-Distilled.i1-Q6_K.gguf}"
+MODEL_ID="${LOCALLLM_BENCH_MODEL_ID:-$(basename "$MODEL_PATH")}" 
+MODEL_ID="${MODEL_ID%.gguf}"
 SERVER_BIN="$ROOT/target/release/localllm.exe"
 LOG_DIR="$ROOT/logs"
 SERVER_LOG="$LOG_DIR/autoresearch-server.log"
@@ -39,4 +41,5 @@ SERVER_PID=$!
 
 python "$ROOT/experiments/bench_chat_latency.py" \
     --base-url "http://$HOST" \
+    --model-id "$MODEL_ID" \
     --server-log "$SERVER_LOG"

experiments/bench_chat_latency.py

@@ -9,21 +9,6 @@ import urllib.error
 import urllib.request
 
 
-PAYLOAD = {
-    "model": "local-model",
-    "stream": False,
-    "temperature": 0.0,
-    "top_p": 1.0,
-    "max_completion_tokens": 48,
-    "messages": [
-        {
-            "role": "user",
-            "content": "Write a compact Rust function that parses a comma-separated list of u32 values and returns a Vec<u32> while ignoring empty segments.",
-        }
-    ],
-}
-
-
 def percentile(sorted_values, pct):
     if not sorted_values:
         return 0.0
@@ -63,8 +48,24 @@ def wait_for_health(base_url, timeout_s, server_log):
     sys.exit(1)
 
 
-def run_once(base_url):
-    body = json.dumps(PAYLOAD).encode("utf-8")
+def build_payload(model_id):
+    return {
+        "model": model_id,
+        "stream": False,
+        "temperature": 0.0,
+        "top_p": 1.0,
+        "max_completion_tokens": 48,
+        "messages": [
+            {
+                "role": "user",
+                "content": "Write a compact Rust function that parses a comma-separated list of u32 values and returns a Vec<u32> while ignoring empty segments.",
+            }
+        ],
+    }
+
+
+def run_once(base_url, model_id):
+    body = json.dumps(build_payload(model_id)).encode("utf-8")
     req = urllib.request.Request(
         base_url + "/v1/chat/completions",
         data=body,
@@ -82,6 +83,7 @@ def run_once(base_url):
 def main():
     parser = argparse.ArgumentParser()
     parser.add_argument("--base-url", required=True)
+    parser.add_argument("--model-id", required=True)
     parser.add_argument("--server-log", default="")
     parser.add_argument("--warmups", type=int, default=1)
     parser.add_argument("--samples", type=int, default=7)
@@ -91,12 +93,12 @@ def main():
     wait_for_health(args.base_url, args.health_timeout, args.server_log)
 
     for _ in range(args.warmups):
-        run_once(args.base_url)
+        run_once(args.base_url, args.model_id)
 
     latencies = []
     tps_values = []
     for _ in range(args.samples):
-        latency_ms, tps = run_once(args.base_url)
+        latency_ms, tps = run_once(args.base_url, args.model_id)
         latencies.append(latency_ms)
         tps_values.append(tps)