12591282da
Major rewrite based on deep study of Karpathy's autoresearch repo.
Architecture changes:
- Multi-experiment support: .autoresearch/{domain}/{name}/ structure
- Domain categories: engineering, marketing, content, prompts, custom
- Project-level (git-tracked, shareable) or user-level (~/.autoresearch/) scope
- User chooses scope during setup, not installation
New evaluators (8 ready-to-use):
- Free: benchmark_speed, benchmark_size, test_pass_rate, build_speed, memory_usage
- LLM judge (uses existing subscription): llm_judge_content, llm_judge_prompt, llm_judge_copy
- LLM judges call user's CLI tool (claude/codex/gemini) — no extra API keys needed
Script improvements:
- setup_experiment.py: --domain, --scope, --evaluator, --list, --list-evaluators
- run_experiment.py: --experiment domain/name, --resume, --loop, --single
- log_results.py: --dashboard, --domain, --format csv|markdown|terminal, --output
Results export:
- Terminal (default), CSV, and Markdown formats
- Per-experiment, per-domain, or cross-experiment dashboard view
SKILL.md rewritten:
- Clear activation triggers (when the skill should activate)
- Practical examples for each domain
- Evaluator documentation with cost transparency
- Simplified loop protocol matching Karpathy's original philosophy
53 lines
1.6 KiB
Python
53 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 os
|
|
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])
|
|
mb = val / (1024 * 1024)
|
|
print(f"peak_mb: {mb:.1f}")
|
|
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)
|