From e28dc13cd5d3c5b4a514bf95f16694173a6237ea Mon Sep 17 00:00:00 2001
From: "memosr.eth" <96793918+memosr@users.noreply.github.com>
Date: Sun, 8 Mar 2026 22:38:02 +0300
Subject: [PATCH] fix: store and close log file handles in rl_training_tool

---
 tools/rl_training_tool.py | 21 ++++++++++++++++++---
 1 file changed, 18 insertions(+), 3 deletions(-)

diff --git a/tools/rl_training_tool.py b/tools/rl_training_tool.py
index 6ffa6e237..bf4c6ad64 100644
--- a/tools/rl_training_tool.py
+++ b/tools/rl_training_tool.py
@@ -323,7 +323,10 @@ async def _spawn_training_run(run_state: RunState, config_path: Path):
         # Step 1: Start the Atropos API server (run-api)
         print(f"[{run_id}] Starting Atropos API server (run-api)...")
         
-        api_log_file = open(api_log, "w")
+        # File must stay open while the subprocess runs; we store the handle
+        # on run_state so _stop_training_run() can close it when done.
+        api_log_file = open(api_log, "w")  # closed by _stop_training_run
+        run_state.api_log_file = api_log_file
         run_state.api_process = subprocess.Popen(
             ["run-api"],
             stdout=api_log_file,
@@ -344,7 +347,8 @@ async def _spawn_training_run(run_state: RunState, config_path: Path):
         # Step 2: Start the Tinker trainer
         print(f"[{run_id}] Starting Tinker trainer: launch_training.py --config {config_path}")
         
-        trainer_log_file = open(trainer_log, "w")
+        trainer_log_file = open(trainer_log, "w")  # closed by _stop_training_run
+        run_state.trainer_log_file = trainer_log_file
         run_state.trainer_process = subprocess.Popen(
             [sys.executable, "launch_training.py", "--config", str(config_path)],
             stdout=trainer_log_file,
@@ -384,7 +388,8 @@ async def _spawn_training_run(run_state: RunState, config_path: Path):
         
         print(f"[{run_id}] Starting environment: {env_info.file_path} serve")
         
-        env_log_file = open(env_log, "w")
+        env_log_file = open(env_log, "w")  # closed by _stop_training_run
+        run_state.env_log_file = env_log_file
         run_state.env_process = subprocess.Popen(
             [sys.executable, str(env_info.file_path), "serve", "--config", str(config_path)],
             stdout=env_log_file,
@@ -480,6 +485,16 @@ def _stop_training_run(run_state: RunState):
     if run_state.status == "running":
         run_state.status = "stopped"
 
+    # Close log file handles that were opened for subprocess stdout.
+    for attr in ("env_log_file", "trainer_log_file", "api_log_file"):
+        fh = getattr(run_state, attr, None)
+        if fh is not None:
+            try:
+                fh.close()
+            except Exception:
+                pass
+            setattr(run_state, attr, None)
+
 
 # ============================================================================
 # Environment Discovery Tools