Timmy_Foundation/hermes-agent
15
0
Fork 0
Code Issues 63 Pull Requests 1 Actions 1 Packages Projects Releases Wiki Activity

fix: store and close log file handles in rl_training_tool

Browse Source
This commit is contained in:
memosr.eth
2026-03-08 22:38:02 +03:00
committed by GitHub
parent cd77c7100c
commit e28dc13cd5
1 changed files with 18 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

21
tools/rl_training_tool.py
View File

@@ -323,7 +323,10 @@ async def _spawn_training_run(run_state: RunState, config_path: Path):
# Step 1: Start the Atropos API server (run-api) # Step 1: Start the Atropos API server (run-api)
print(f"[{run_id}] Starting 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_state.api_process = subprocess.Popen(
["run-api"], ["run-api"],
stdout=api_log_file, 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 # Step 2: Start the Tinker trainer
print(f"[{run_id}] Starting Tinker trainer: launch_training.py --config {config_path}") 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( run_state.trainer_process = subprocess.Popen(
[sys.executable, "launch_training.py", "--config", str(config_path)], [sys.executable, "launch_training.py", "--config", str(config_path)],
stdout=trainer_log_file, 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") 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( run_state.env_process = subprocess.Popen(
[sys.executable, str(env_info.file_path), "serve", "--config", str(config_path)], [sys.executable, str(env_info.file_path), "serve", "--config", str(config_path)],
stdout=env_log_file, stdout=env_log_file,
@@ -480,6 +485,16 @@ def _stop_training_run(run_state: RunState):
if run_state.status == "running": if run_state.status == "running":
run_state.status = "stopped" 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 # Environment Discovery Tools