7911cf957a
**Bug fixes (run_experiment.py):** - Fix broken revert logic: was saving HEAD as pre_commit (no-op revert), now uses git reset --hard HEAD~1 for correct rollback - Remove broken --loop mode (agent IS the loop, script handles one iteration) - Fix shell injection: all git commands use subprocess list form - Replace shell tail with Python file read **Bug fixes (other scripts):** - setup_experiment.py: fix shell injection in git branch creation, remove dead --skip-baseline flag, fix evaluator docstring parsing - log_results.py: fix 6 falsy-zero bugs (baseline=0 treated as None), add domain_filter to CSV/markdown export, move import time to top - evaluators: add FileNotFoundError handling, fix output format mismatch in llm_judge_copy, add peak_kb on macOS, add ValueError handling **Plugin packaging (NEW):** - plugin.json, settings.json, CLAUDE.md for plugin registry - 5 slash commands: /ar:setup, /ar:run, /ar:loop, /ar:status, /ar:resume - /ar:loop supports user-selected intervals (10m, 1h, daily, weekly, monthly) - experiment-runner agent for autonomous loop iterations - Registered in marketplace.json as plugin #20 **SKILL.md rewrite:** - Replace ambiguous "Loop Protocol" with clear "Agent Protocol" - Add results.tsv format spec, strategy escalation, self-improvement - Replace "NEVER STOP" with resumable stopping logic **Docs & sync:** - Codex (157 skills), Gemini (229 items), convert.sh all pick up the skill - 6 new MkDocs pages, mkdocs.yml nav updated - Counts updated: 17 agents, 22 slash commands Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
54 lines
1.6 KiB
Python
54 lines
1.6 KiB
Python
#!/usr/bin/env python3
|
|
"""Measure peak memory usage of a command.
|
|
DO NOT MODIFY after experiment starts — this is the fixed evaluator."""
|
|
|
|
import platform
|
|
import subprocess
|
|
import sys
|
|
|
|
# --- CONFIGURE THESE ---
|
|
COMMAND = "python src/module.py" # Command to measure
|
|
# --- END CONFIG ---
|
|
|
|
system = platform.system()
|
|
|
|
if system == "Linux":
|
|
# Use /usr/bin/time for peak RSS
|
|
result = subprocess.run(
|
|
f"/usr/bin/time -v {COMMAND}",
|
|
shell=True, capture_output=True, text=True, timeout=300
|
|
)
|
|
output = result.stderr
|
|
for line in output.splitlines():
|
|
if "Maximum resident set size" in line:
|
|
kb = int(line.split(":")[-1].strip())
|
|
mb = kb / 1024
|
|
print(f"peak_mb: {mb:.1f}")
|
|
print(f"peak_kb: {kb}")
|
|
sys.exit(0)
|
|
print("Could not parse memory from /usr/bin/time output", file=sys.stderr)
|
|
sys.exit(1)
|
|
|
|
elif system == "Darwin":
|
|
# macOS: use /usr/bin/time -l
|
|
result = subprocess.run(
|
|
f"/usr/bin/time -l {COMMAND}",
|
|
shell=True, capture_output=True, text=True, timeout=300
|
|
)
|
|
output = result.stderr
|
|
for line in output.splitlines():
|
|
if "maximum resident set size" in line.lower():
|
|
# macOS reports in bytes
|
|
val = int(line.strip().split()[0])
|
|
kb = val / 1024
|
|
mb = val / (1024 * 1024)
|
|
print(f"peak_mb: {mb:.1f}")
|
|
print(f"peak_kb: {int(kb)}")
|
|
sys.exit(0)
|
|
print("Could not parse memory from time output", file=sys.stderr)
|
|
sys.exit(1)
|
|
|
|
else:
|
|
print(f"Unsupported platform: {system}. Use Linux or macOS.", file=sys.stderr)
|
|
sys.exit(1)
|