Baseline shortened: 11-task subset (1 per category + T01), max_tokens 16384, settings in README; baseline_chain.sh

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_014aUaQeLnwbb1zTpN7kHeat

train/baseline.py

@@ -17,6 +17,7 @@ from harness.runner import Runner  # noqa: E402
 
 MODEL = os.path.expanduser("~/models/Qwen3.8-27B-4bit")
 BASE_URL = "http://127.0.0.1:8080/v1"
+MAX_TOKENS = 16384  # per turn; sent in each request (the server limit stays 32768). Same for before/after.
 
 
 def main():
@@ -30,13 +31,15 @@ def main():
     out_path = os.path.join(ROOT, "runs", "stage1", f"{a.label}.json")
     os.makedirs(os.path.dirname(out_path), exist_ok=True)
     res = json.load(open(out_path)) if os.path.exists(out_path) else {"model": MODEL, "tasks": {}}
+    res["settings"] = {"max_tokens": MAX_TOKENS, "reasoning_effort": "medium", "temperature": 0.2, "tool_call_budget": 60,
+                       "subset": "train/subset.json", "date": "2026-10-03"}
     runs_root = os.path.join(ROOT, "runs", "stage1", a.label)
     for i, t in enumerate(subset):
         tid = t["id"]
         if (a.only and tid not in a.only) or tid in res["tasks"]:
             continue
         pool = os.path.join(ROOT, "tasks") if tid.startswith("T") else os.path.join(ROOT, "tasks_gen", "eval")
-        agent = LlmAgent(MODEL, BASE_URL)
+        agent = LlmAgent(MODEL, BASE_URL, max_tokens=MAX_TOKENS)
         try:
             rep, run_dir = Runner(pool, runs_root).run(tid, agent, a.run_base + i)
         except Exception as e:  # noqa: BLE001  one broken run must not stop the series