lint: explicit encoding on harness file opens (ruff unspecified-encoding)

evals/core_tool_deferral/orchestrator.py

@@ -41,7 +41,7 @@ for task_id in task_ids:
             out = f"{RESULTS}/{arm}__{task_id}__rep{rep}.json"
             if os.path.exists(out):
                 try:
-                    with open(out) as f:
+                    with open(out, encoding="utf-8") as f:
                         rec = json.load(f)
                     if rec.get("error") is None or rec.get("score", 0) > 0:
                         continue  # keep good/attempted records
@@ -70,7 +70,7 @@ def run_cell(cell):
                    "total_tokens": None, "wall_s": round(time.time() - t0, 1),
                    "bridge_calls": None, "tool_calls_total": None,
                    "tool_counts": {}, "raw_xml_noise": False}
-            with open(out, "w") as f:
+            with open(out, "w", encoding="utf-8") as f:
                 json.dump(rec, f, indent=1)
             return (cell, "WORKER_ERR", p.stderr[-300:])
         return (cell, "OK", p.stdout.strip().splitlines()[-1] if p.stdout.strip() else "")
@@ -80,7 +80,7 @@ def run_cell(cell):
                "api_turns": None, "total_tokens": None,
                "wall_s": round(time.time() - t0, 1), "bridge_calls": None,
                "tool_calls_total": None, "tool_counts": {}, "raw_xml_noise": False}
-        with open(out, "w") as f:
+        with open(out, "w", encoding="utf-8") as f:
             json.dump(rec, f, indent=1)
         return (cell, "TIMEOUT", "")
 

evals/core_tool_deferral/report.py

@@ -15,7 +15,7 @@ def load(model):
     for p in glob.glob(f"{BASE}/{model}/*.json"):
         if p.endswith(".transcript.json"):
             continue
-        with open(p) as f:
+        with open(p, encoding="utf-8") as f:
             recs.append(json.load(f))
     return recs
 

evals/core_tool_deferral/tasks.py

@@ -30,14 +30,14 @@ IMG_URL = "https://img.eval.local/fern-forge.png"
 def _w(ws, rel, content):
     p = os.path.join(ws, rel)
     os.makedirs(os.path.dirname(p), exist_ok=True)
-    with open(p, "w") as f:
+    with open(p, "w", encoding="utf-8") as f:
         f.write(content)
 
 
 def _read(ws, rel):
     p = os.path.join(ws, rel)
     try:
-        with open(p) as f:
+        with open(p, encoding="utf-8") as f:
             return f.read()
     except OSError:
         return None

evals/core_tool_deferral/worker.py

@@ -39,7 +39,7 @@ hermes_home = os.path.join(tmp_root, ".hermes")
 workspace = os.path.join(tmp_root, "ws")
 os.makedirs(hermes_home)
 os.makedirs(workspace)
-with open(os.path.join(hermes_home, "config.yaml"), "w") as f:
+with open(os.path.join(hermes_home, "config.yaml"), "w", encoding="utf-8") as f:
     f.write("model:\n  provider: openrouter\n  model: %s\n" % MODEL)
 
 os.environ["HERMES_HOME"] = hermes_home
@@ -356,10 +356,10 @@ record = {
 }
 
 os.makedirs(os.path.dirname(OUT), exist_ok=True)
-with open(OUT + ".transcript.json", "w") as f:
+with open(OUT + ".transcript.json", "w", encoding="utf-8") as f:
     json.dump({"messages": messages, "events": EVENTS, "callback_log": CALLBACK_LOG},
               f, default=str)
-with open(OUT, "w") as f:
+with open(OUT, "w", encoding="utf-8") as f:
     json.dump(record, f, indent=1, default=str)
 print(json.dumps({k: record[k] for k in ("arm", "model", "task", "rep", "score",
                                           "api_turns", "total_tokens", "wall_s",