APEX/BrowserUse_and_ComputerUse_skills
5
0
Fork 0
Code Issues 6 Pull requests 1 Projects 1 Releases Packages Wiki Activity Actions

Merge branch 'main' into fix/packaging-bugs

Browse source
This commit is contained in:
Teknium 2026-03-13 03:15:45 -07:00 • committed by GitHub
commit 0a88b133c2
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
289 changed files with 48243 additions and 3815 deletions
Download patch file Download diff file Expand all files Collapse all files

41
tools/rl_training_tool.py
View file

@ -54,9 +54,10 @@ ENVIRONMENTS_DIR = TINKER_ATROPOS_ROOT / "tinker_atropos" / "environments"
CONFIGS_DIR = TINKER_ATROPOS_ROOT / "configs"
LOGS_DIR = Path(os.getenv("HERMES_HOME", Path.home() / ".hermes")) / "logs" / "rl_training"
# Ensure logs directory exists
LOGS_DIR.mkdir(parents=True, exist_ok=True)
def _ensure_logs_dir():
"""Lazily create logs directory on first use (avoid side effects at import time)."""
if TINKER_ATROPOS_ROOT.exists():
LOGS_DIR.mkdir(exist_ok=True)
# ============================================================================
# Locked Configuration (Infrastructure Settings)
@ -314,6 +315,8 @@ async def _spawn_training_run(run_state: RunState, config_path: Path):
"""
run_id = run_state.run_id
_ensure_logs_dir()
# Log file paths
api_log = LOGS_DIR / f"api_{run_id}.log"
trainer_log = LOGS_DIR / f"trainer_{run_id}.log"
@ -323,7 +326,10 @@ 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,
@ -337,6 +343,7 @@ async def _spawn_training_run(run_state: RunState, config_path: Path):
if run_state.api_process.poll() is not None:
run_state.status = "failed"
run_state.error_message = f"API server exited with code {run_state.api_process.returncode}. Check {api_log}"
_stop_training_run(run_state)
return
print(f"[{run_id}] Atropos API server started")
@ -344,7 +351,8 @@ 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,
@ -360,8 +368,7 @@ async def _spawn_training_run(run_state: RunState, config_path: Path):
if run_state.trainer_process.poll() is not None:
run_state.status = "failed"
run_state.error_message = f"Trainer exited with code {run_state.trainer_process.returncode}. Check {trainer_log}"
if run_state.api_process:
run_state.api_process.terminate()
_stop_training_run(run_state)
return
print(f"[{run_id}] Trainer started, inference server on port 8001")
@ -380,11 +387,13 @@ async def _spawn_training_run(run_state: RunState, config_path: Path):
if not env_info:
run_state.status = "failed"
run_state.error_message = f"Environment '{run_state.environment}' not found"
_stop_training_run(run_state)
return
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,
@ -398,10 +407,7 @@ async def _spawn_training_run(run_state: RunState, config_path: Path):
if run_state.env_process.poll() is not None:
run_state.status = "failed"
run_state.error_message = f"Environment exited with code {run_state.env_process.returncode}. Check {env_log}"
if run_state.trainer_process:
run_state.trainer_process.terminate()
if run_state.api_process:
run_state.api_process.terminate()
_stop_training_run(run_state)
return
run_state.status = "running"
@ -480,6 +486,16 @@ 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
@ -1079,6 +1095,7 @@ async def rl_test_inference(
}
# Create output directory for test results
_ensure_logs_dir()
test_output_dir = LOGS_DIR / "inference_tests"
test_output_dir.mkdir(exist_ok=True)