refactor: autoresearch-agent v2.0 — multi-experiment, multi-domain, real-world evaluators
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
This commit is contained in:
Leo
@@ -1,125 +1,389 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
autoresearch-agent: Results Logger
|
||||
autoresearch-agent: Results Viewer
|
||||
|
||||
View and analyze experiment results from results.tsv.
|
||||
View experiment results in multiple formats: terminal, CSV, Markdown.
|
||||
Supports single experiment, domain, or cross-experiment dashboard.
|
||||
|
||||
Usage:
|
||||
python scripts/log_results.py --summary # Print progress table
|
||||
python scripts/log_results.py --best # Show best result
|
||||
python scripts/log_results.py --history # Full experiment history
|
||||
python scripts/log_results.py --record commit val status desc # Add entry manually
|
||||
python scripts/log_results.py --experiment engineering/api-speed
|
||||
python scripts/log_results.py --domain engineering
|
||||
python scripts/log_results.py --dashboard
|
||||
python scripts/log_results.py --experiment engineering/api-speed --format csv --output results.csv
|
||||
python scripts/log_results.py --experiment engineering/api-speed --format markdown --output results.md
|
||||
python scripts/log_results.py --dashboard --format markdown --output dashboard.md
|
||||
"""
|
||||
|
||||
import argparse
|
||||
import csv
|
||||
import io
|
||||
import sys
|
||||
from pathlib import Path
|
||||
|
||||
|
||||
def load_results(path):
|
||||
tsv = Path(path) / "results.tsv"
|
||||
def find_autoresearch_root():
|
||||
"""Find .autoresearch/ in project or user home."""
|
||||
project_root = Path(".").resolve() / ".autoresearch"
|
||||
if project_root.exists():
|
||||
return project_root
|
||||
user_root = Path.home() / ".autoresearch"
|
||||
if user_root.exists():
|
||||
return user_root
|
||||
return None
|
||||
|
||||
|
||||
def load_config(experiment_dir):
|
||||
"""Load config.cfg."""
|
||||
cfg_file = experiment_dir / "config.cfg"
|
||||
config = {}
|
||||
if cfg_file.exists():
|
||||
for line in cfg_file.read_text().splitlines():
|
||||
if ":" in line:
|
||||
k, v = line.split(":", 1)
|
||||
config[k.strip()] = v.strip()
|
||||
return config
|
||||
|
||||
|
||||
def load_results(experiment_dir):
|
||||
"""Load results.tsv into list of dicts."""
|
||||
tsv = experiment_dir / "results.tsv"
|
||||
if not tsv.exists():
|
||||
return []
|
||||
lines = tsv.read_text().splitlines()[1:] # skip header
|
||||
results = []
|
||||
for line in lines:
|
||||
for line in tsv.read_text().splitlines()[1:]:
|
||||
parts = line.split("\t")
|
||||
if len(parts) >= 4:
|
||||
try:
|
||||
metric_val = float(parts[1]) if parts[1] != "N/A" else None
|
||||
metric = float(parts[1]) if parts[1] != "N/A" else None
|
||||
except ValueError:
|
||||
metric_val = None
|
||||
metric = None
|
||||
results.append({
|
||||
"commit": parts[0],
|
||||
"metric": metric_val,
|
||||
"metric": metric,
|
||||
"status": parts[2],
|
||||
"description": parts[3]
|
||||
"description": parts[3],
|
||||
})
|
||||
return results
|
||||
|
||||
|
||||
def print_summary(results, metric_name="metric", direction="lower"):
|
||||
if not results:
|
||||
print("No experiments logged yet.")
|
||||
return
|
||||
|
||||
def compute_stats(results, direction):
|
||||
"""Compute statistics from results."""
|
||||
keeps = [r for r in results if r["status"] == "keep"]
|
||||
discards = [r for r in results if r["status"] == "discard"]
|
||||
crashes = [r for r in results if r["status"] == "crash"]
|
||||
|
||||
print(f"\n{'─'*60}")
|
||||
print(f" autoresearch-agent — Results Summary")
|
||||
print(f"{'─'*60}")
|
||||
print(f" Total experiments: {len(results)}")
|
||||
print(f" ✅ Keep: {len(keeps):3d} ({len(keeps)/max(len(results),1)*100:.0f}%)")
|
||||
print(f" ❌ Discard: {len(discards):3d} ({len(discards)/max(len(results),1)*100:.0f}%)")
|
||||
print(f" 💥 Crash: {len(crashes):3d} ({len(crashes)/max(len(results),1)*100:.0f}%)")
|
||||
valid_keeps = [r for r in keeps if r["metric"] is not None]
|
||||
baseline = valid_keeps[0]["metric"] if valid_keeps else None
|
||||
if valid_keeps:
|
||||
best = min(r["metric"] for r in valid_keeps) if direction == "lower" else max(r["metric"] for r in valid_keeps)
|
||||
else:
|
||||
best = None
|
||||
|
||||
if keeps:
|
||||
valid = [r for r in keeps if r["metric"] is not None]
|
||||
if valid:
|
||||
baseline = valid[0]["metric"]
|
||||
best = min(r["metric"] for r in valid) if direction == "lower" else max(r["metric"] for r in valid)
|
||||
best_run = next(r for r in valid if r["metric"] == best)
|
||||
improvement = ((baseline - best) / baseline * 100) if direction == "lower" else ((best - baseline) / baseline * 100)
|
||||
pct_change = None
|
||||
if baseline and best and baseline != 0:
|
||||
if direction == "lower":
|
||||
pct_change = (baseline - best) / baseline * 100
|
||||
else:
|
||||
pct_change = (best - baseline) / baseline * 100
|
||||
|
||||
print(f"\n {metric_name}:")
|
||||
print(f" Baseline: {baseline:.6f}")
|
||||
print(f" Best: {best:.6f} (commit: {best_run['commit']})")
|
||||
print(f" Change: {improvement:+.2f}%")
|
||||
|
||||
print(f"{'─'*60}\n")
|
||||
return {
|
||||
"total": len(results),
|
||||
"keeps": len(keeps),
|
||||
"discards": len(discards),
|
||||
"crashes": len(crashes),
|
||||
"baseline": baseline,
|
||||
"best": best,
|
||||
"pct_change": pct_change,
|
||||
}
|
||||
|
||||
|
||||
def print_history(results):
|
||||
# --- Terminal Output ---
|
||||
|
||||
def print_experiment(experiment_dir, experiment_path):
|
||||
"""Print single experiment results to terminal."""
|
||||
config = load_config(experiment_dir)
|
||||
results = load_results(experiment_dir)
|
||||
direction = config.get("metric_direction", "lower")
|
||||
metric_name = config.get("metric", "metric")
|
||||
|
||||
if not results:
|
||||
print("No experiments logged yet.")
|
||||
print(f"No results for {experiment_path}")
|
||||
return
|
||||
|
||||
print(f"\n{'COMMIT':8} {'METRIC':10} {'STATUS':8} DESCRIPTION")
|
||||
print("─" * 60)
|
||||
for r in results:
|
||||
metric_str = f"{r['metric']:.6f}" if r['metric'] is not None else "crash "
|
||||
status_icon = {"keep": "✅", "discard": "❌", "crash": "💥"}.get(r["status"], "?")
|
||||
print(f"{r['commit']:8} {metric_str:10} {status_icon} {r['description'][:40]}")
|
||||
stats = compute_stats(results, direction)
|
||||
|
||||
print(f"\n{'─' * 65}")
|
||||
print(f" {experiment_path}")
|
||||
print(f" Target: {config.get('target', '?')} | Metric: {metric_name} ({direction})")
|
||||
print(f"{'─' * 65}")
|
||||
print(f" Total: {stats['total']} | Keep: {stats['keeps']} | Discard: {stats['discards']} | Crash: {stats['crashes']}")
|
||||
|
||||
if stats["baseline"] is not None and stats["best"] is not None:
|
||||
pct = f" ({stats['pct_change']:+.1f}%)" if stats["pct_change"] is not None else ""
|
||||
print(f" Baseline: {stats['baseline']:.6f} -> Best: {stats['best']:.6f}{pct}")
|
||||
|
||||
print(f"\n {'COMMIT':<10} {'METRIC':>12} {'STATUS':<10} DESCRIPTION")
|
||||
print(f" {'─' * 60}")
|
||||
for r in results:
|
||||
m = f"{r['metric']:.6f}" if r["metric"] is not None else "N/A "
|
||||
icon = {"keep": "+", "discard": "-", "crash": "!"}.get(r["status"], "?")
|
||||
print(f" {r['commit']:<10} {m:>12} {icon} {r['status']:<7} {r['description'][:35]}")
|
||||
print()
|
||||
|
||||
|
||||
def print_dashboard(root):
|
||||
"""Print cross-experiment dashboard."""
|
||||
experiments = []
|
||||
for domain_dir in sorted(root.iterdir()):
|
||||
if not domain_dir.is_dir() or domain_dir.name.startswith("."):
|
||||
continue
|
||||
for exp_dir in sorted(domain_dir.iterdir()):
|
||||
if not exp_dir.is_dir() or not (exp_dir / "config.cfg").exists():
|
||||
continue
|
||||
config = load_config(exp_dir)
|
||||
results = load_results(exp_dir)
|
||||
direction = config.get("metric_direction", "lower")
|
||||
stats = compute_stats(results, direction)
|
||||
|
||||
# Determine status
|
||||
status = "idle"
|
||||
if stats["total"] > 0:
|
||||
tsv = exp_dir / "results.tsv"
|
||||
if tsv.exists():
|
||||
import time
|
||||
age_hours = (time.time() - tsv.stat().st_mtime) / 3600
|
||||
status = "active" if age_hours < 1 else "paused" if age_hours < 24 else "done"
|
||||
|
||||
best_str = f"{stats['best']:.4f}" if stats["best"] is not None else "—"
|
||||
pct_str = f"{stats['pct_change']:+.1f}%" if stats["pct_change"] is not None else "—"
|
||||
|
||||
experiments.append({
|
||||
"domain": domain_dir.name,
|
||||
"name": exp_dir.name,
|
||||
"runs": stats["total"],
|
||||
"kept": stats["keeps"],
|
||||
"best": best_str,
|
||||
"change": pct_str,
|
||||
"status": status,
|
||||
"metric": config.get("metric", "?"),
|
||||
})
|
||||
|
||||
if not experiments:
|
||||
print("No experiments found.")
|
||||
return experiments
|
||||
|
||||
print(f"\n{'─' * 90}")
|
||||
print(f" autoresearch — Dashboard")
|
||||
print(f"{'─' * 90}")
|
||||
print(f" {'DOMAIN':<15} {'EXPERIMENT':<20} {'RUNS':>5} {'KEPT':>5} {'BEST':>12} {'CHANGE':>10} {'STATUS':<8}")
|
||||
print(f" {'─' * 85}")
|
||||
for e in experiments:
|
||||
print(f" {e['domain']:<15} {e['name']:<20} {e['runs']:>5} {e['kept']:>5} {e['best']:>12} {e['change']:>10} {e['status']:<8}")
|
||||
print()
|
||||
return experiments
|
||||
|
||||
|
||||
# --- CSV Export ---
|
||||
|
||||
def export_experiment_csv(experiment_dir, experiment_path):
|
||||
"""Export single experiment as CSV string."""
|
||||
config = load_config(experiment_dir)
|
||||
results = load_results(experiment_dir)
|
||||
direction = config.get("metric_direction", "lower")
|
||||
stats = compute_stats(results, direction)
|
||||
|
||||
buf = io.StringIO()
|
||||
writer = csv.writer(buf)
|
||||
|
||||
# Header with metadata
|
||||
writer.writerow(["# Experiment", experiment_path])
|
||||
writer.writerow(["# Target", config.get("target", "")])
|
||||
writer.writerow(["# Metric", f"{config.get('metric', '')} ({direction} is better)"])
|
||||
if stats["baseline"] is not None:
|
||||
writer.writerow(["# Baseline", f"{stats['baseline']:.6f}"])
|
||||
if stats["best"] is not None:
|
||||
pct = f" ({stats['pct_change']:+.1f}%)" if stats["pct_change"] else ""
|
||||
writer.writerow(["# Best", f"{stats['best']:.6f}{pct}"])
|
||||
writer.writerow(["# Total", stats["total"]])
|
||||
writer.writerow(["# Keep/Discard/Crash", f"{stats['keeps']}/{stats['discards']}/{stats['crashes']}"])
|
||||
writer.writerow([])
|
||||
|
||||
writer.writerow(["Commit", "Metric", "Status", "Description"])
|
||||
for r in results:
|
||||
m = f"{r['metric']:.6f}" if r["metric"] is not None else "N/A"
|
||||
writer.writerow([r["commit"], m, r["status"], r["description"]])
|
||||
|
||||
return buf.getvalue()
|
||||
|
||||
|
||||
def export_dashboard_csv(root):
|
||||
"""Export dashboard as CSV string."""
|
||||
experiments = []
|
||||
for domain_dir in sorted(root.iterdir()):
|
||||
if not domain_dir.is_dir() or domain_dir.name.startswith("."):
|
||||
continue
|
||||
for exp_dir in sorted(domain_dir.iterdir()):
|
||||
if not exp_dir.is_dir() or not (exp_dir / "config.cfg").exists():
|
||||
continue
|
||||
config = load_config(exp_dir)
|
||||
results = load_results(exp_dir)
|
||||
direction = config.get("metric_direction", "lower")
|
||||
stats = compute_stats(results, direction)
|
||||
best_str = f"{stats['best']:.6f}" if stats["best"] else ""
|
||||
pct_str = f"{stats['pct_change']:+.1f}%" if stats["pct_change"] else ""
|
||||
experiments.append([
|
||||
domain_dir.name, exp_dir.name, config.get("metric", ""),
|
||||
stats["total"], stats["keeps"], stats["discards"], stats["crashes"],
|
||||
best_str, pct_str
|
||||
])
|
||||
|
||||
buf = io.StringIO()
|
||||
writer = csv.writer(buf)
|
||||
writer.writerow(["Domain", "Experiment", "Metric", "Runs", "Kept", "Discarded", "Crashed", "Best", "Change"])
|
||||
for e in experiments:
|
||||
writer.writerow(e)
|
||||
return buf.getvalue()
|
||||
|
||||
|
||||
# --- Markdown Export ---
|
||||
|
||||
def export_experiment_markdown(experiment_dir, experiment_path):
|
||||
"""Export single experiment as Markdown string."""
|
||||
config = load_config(experiment_dir)
|
||||
results = load_results(experiment_dir)
|
||||
direction = config.get("metric_direction", "lower")
|
||||
metric_name = config.get("metric", "metric")
|
||||
stats = compute_stats(results, direction)
|
||||
|
||||
lines = []
|
||||
lines.append(f"# Autoresearch: {experiment_path}\n")
|
||||
lines.append(f"**Target:** `{config.get('target', '?')}` ")
|
||||
lines.append(f"**Metric:** `{metric_name}` ({direction} is better) ")
|
||||
lines.append(f"**Experiments:** {stats['total']} total — {stats['keeps']} kept, {stats['discards']} discarded, {stats['crashes']} crashed\n")
|
||||
|
||||
if stats["baseline"] is not None and stats["best"] is not None:
|
||||
pct = f" ({stats['pct_change']:+.1f}%)" if stats["pct_change"] else ""
|
||||
lines.append(f"**Progress:** `{stats['baseline']:.6f}` → `{stats['best']:.6f}`{pct}\n")
|
||||
|
||||
lines.append(f"| Commit | Metric | Status | Description |")
|
||||
lines.append(f"|--------|--------|--------|-------------|")
|
||||
for r in results:
|
||||
m = f"`{r['metric']:.6f}`" if r["metric"] is not None else "N/A"
|
||||
lines.append(f"| `{r['commit']}` | {m} | {r['status']} | {r['description']} |")
|
||||
lines.append("")
|
||||
|
||||
return "\n".join(lines)
|
||||
|
||||
|
||||
def export_dashboard_markdown(root):
|
||||
"""Export dashboard as Markdown string."""
|
||||
lines = []
|
||||
lines.append("# Autoresearch Dashboard\n")
|
||||
lines.append("| Domain | Experiment | Metric | Runs | Kept | Best | Change | Status |")
|
||||
lines.append("|--------|-----------|--------|------|------|------|--------|--------|")
|
||||
|
||||
for domain_dir in sorted(root.iterdir()):
|
||||
if not domain_dir.is_dir() or domain_dir.name.startswith("."):
|
||||
continue
|
||||
for exp_dir in sorted(domain_dir.iterdir()):
|
||||
if not exp_dir.is_dir() or not (exp_dir / "config.cfg").exists():
|
||||
continue
|
||||
config = load_config(exp_dir)
|
||||
results = load_results(exp_dir)
|
||||
direction = config.get("metric_direction", "lower")
|
||||
stats = compute_stats(results, direction)
|
||||
best = f"`{stats['best']:.4f}`" if stats["best"] else "—"
|
||||
pct = f"{stats['pct_change']:+.1f}%" if stats["pct_change"] else "—"
|
||||
|
||||
import time
|
||||
tsv = exp_dir / "results.tsv"
|
||||
status = "idle"
|
||||
if tsv.exists() and stats["total"] > 0:
|
||||
age_h = (time.time() - tsv.stat().st_mtime) / 3600
|
||||
status = "active" if age_h < 1 else "paused" if age_h < 24 else "done"
|
||||
|
||||
lines.append(f"| {domain_dir.name} | {exp_dir.name} | {config.get('metric', '?')} | {stats['total']} | {stats['keeps']} | {best} | {pct} | {status} |")
|
||||
|
||||
lines.append("")
|
||||
return "\n".join(lines)
|
||||
|
||||
|
||||
# --- Main ---
|
||||
|
||||
def main():
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument("--summary", action="store_true")
|
||||
parser.add_argument("--best", action="store_true")
|
||||
parser.add_argument("--history", action="store_true")
|
||||
parser.add_argument("--record", nargs=4, metavar=("COMMIT", "METRIC", "STATUS", "DESC"))
|
||||
parser.add_argument("--path", default=".")
|
||||
parser.add_argument("--metric", default="metric")
|
||||
parser.add_argument("--direction", default="lower", choices=["lower", "higher"])
|
||||
parser = argparse.ArgumentParser(description="autoresearch-agent results viewer")
|
||||
parser.add_argument("--experiment", help="Show one experiment: domain/name")
|
||||
parser.add_argument("--domain", help="Show all experiments in a domain")
|
||||
parser.add_argument("--dashboard", action="store_true", help="Cross-experiment dashboard")
|
||||
parser.add_argument("--format", choices=["terminal", "csv", "markdown"], default="terminal",
|
||||
help="Output format (default: terminal)")
|
||||
parser.add_argument("--output", "-o", help="Write to file instead of stdout")
|
||||
parser.add_argument("--all", action="store_true", help="Show all experiments (alias for --dashboard)")
|
||||
args = parser.parse_args()
|
||||
|
||||
path = Path(args.path).resolve()
|
||||
root = find_autoresearch_root()
|
||||
if root is None:
|
||||
print("No .autoresearch/ found. Run setup_experiment.py first.")
|
||||
sys.exit(1)
|
||||
|
||||
if args.record:
|
||||
commit, metric, status, desc = args.record
|
||||
tsv = path / "results.tsv"
|
||||
if not tsv.exists():
|
||||
tsv.write_text("commit\tmetric\tstatus\tdescription\n")
|
||||
with open(tsv, "a") as f:
|
||||
f.write(f"{commit}\t{metric}\t{status}\t{desc}\n")
|
||||
print(f"✓ Logged: {commit} {metric} {status}")
|
||||
return
|
||||
output_text = None
|
||||
|
||||
results = load_results(path)
|
||||
# Single experiment
|
||||
if args.experiment:
|
||||
experiment_dir = root / args.experiment
|
||||
if not experiment_dir.exists():
|
||||
print(f"Experiment not found: {args.experiment}")
|
||||
sys.exit(1)
|
||||
|
||||
if args.history:
|
||||
print_history(results)
|
||||
elif args.best:
|
||||
keeps = [r for r in results if r["status"] == "keep" and r["metric"]]
|
||||
if not keeps:
|
||||
print("No successful experiments yet.")
|
||||
if args.format == "csv":
|
||||
output_text = export_experiment_csv(experiment_dir, args.experiment)
|
||||
elif args.format == "markdown":
|
||||
output_text = export_experiment_markdown(experiment_dir, args.experiment)
|
||||
else:
|
||||
print_experiment(experiment_dir, args.experiment)
|
||||
return
|
||||
best = min(keeps, key=lambda r: r["metric"]) if args.direction == "lower" else max(keeps, key=lambda r: r["metric"])
|
||||
print(f"Best: {best['metric']:.6f} (commit: {best['commit']}) — {best['description']}")
|
||||
|
||||
# Domain
|
||||
elif args.domain:
|
||||
domain_dir = root / args.domain
|
||||
if not domain_dir.exists():
|
||||
print(f"Domain not found: {args.domain}")
|
||||
sys.exit(1)
|
||||
for exp_dir in sorted(domain_dir.iterdir()):
|
||||
if exp_dir.is_dir() and (exp_dir / "config.cfg").exists():
|
||||
if args.format == "terminal":
|
||||
print_experiment(exp_dir, f"{args.domain}/{exp_dir.name}")
|
||||
# For CSV/MD, fall through to dashboard with domain filter
|
||||
if args.format != "terminal":
|
||||
# Use dashboard export filtered to domain
|
||||
output_text = export_dashboard_csv(root) if args.format == "csv" else export_dashboard_markdown(root)
|
||||
else:
|
||||
return
|
||||
|
||||
# Dashboard
|
||||
elif args.dashboard or args.all:
|
||||
if args.format == "csv":
|
||||
output_text = export_dashboard_csv(root)
|
||||
elif args.format == "markdown":
|
||||
output_text = export_dashboard_markdown(root)
|
||||
else:
|
||||
print_dashboard(root)
|
||||
return
|
||||
|
||||
else:
|
||||
print_summary(results, args.metric, args.direction)
|
||||
# Default: dashboard
|
||||
if args.format == "terminal":
|
||||
print_dashboard(root)
|
||||
return
|
||||
output_text = export_dashboard_csv(root) if args.format == "csv" else export_dashboard_markdown(root)
|
||||
|
||||
# Write output
|
||||
if output_text:
|
||||
if args.output:
|
||||
Path(args.output).write_text(output_text)
|
||||
print(f"Written to {args.output}")
|
||||
else:
|
||||
print(output_text)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
@@ -2,17 +2,15 @@
|
||||
"""
|
||||
autoresearch-agent: Experiment Runner
|
||||
|
||||
Executes the autonomous experiment loop:
|
||||
- Reads .autoresearch.cfg for project config
|
||||
- Runs the target evaluation
|
||||
- Keeps improvements (git commit) or discards failures (git reset)
|
||||
- Logs everything to results.tsv
|
||||
- Loops indefinitely until interrupted
|
||||
Executes the autonomous experiment loop for a specific experiment.
|
||||
Reads config from .autoresearch/{domain}/{name}/config.cfg.
|
||||
|
||||
Usage:
|
||||
python scripts/run_experiment.py --loop # Run forever
|
||||
python scripts/run_experiment.py --single # Run one experiment
|
||||
python scripts/run_experiment.py --dry-run # Show what would happen
|
||||
python scripts/run_experiment.py --experiment engineering/api-speed --loop
|
||||
python scripts/run_experiment.py --experiment engineering/api-speed --single
|
||||
python scripts/run_experiment.py --experiment marketing/medium-ctr --loop
|
||||
python scripts/run_experiment.py --resume --loop
|
||||
python scripts/run_experiment.py --experiment engineering/api-speed --dry-run
|
||||
"""
|
||||
|
||||
import argparse
|
||||
@@ -25,11 +23,22 @@ from datetime import datetime
|
||||
from pathlib import Path
|
||||
|
||||
|
||||
def load_config(path):
|
||||
"""Load .autoresearch.cfg"""
|
||||
cfg_file = Path(path) / ".autoresearch.cfg"
|
||||
def find_autoresearch_root():
|
||||
"""Find .autoresearch/ in project or user home."""
|
||||
project_root = Path(".").resolve() / ".autoresearch"
|
||||
if project_root.exists():
|
||||
return project_root
|
||||
user_root = Path.home() / ".autoresearch"
|
||||
if user_root.exists():
|
||||
return user_root
|
||||
return None
|
||||
|
||||
|
||||
def load_config(experiment_dir):
|
||||
"""Load config.cfg from experiment directory."""
|
||||
cfg_file = experiment_dir / "config.cfg"
|
||||
if not cfg_file.exists():
|
||||
print("✗ No .autoresearch.cfg found. Run setup_experiment.py first.")
|
||||
print(f" Error: no config.cfg in {experiment_dir}")
|
||||
sys.exit(1)
|
||||
config = {}
|
||||
for line in cfg_file.read_text().splitlines():
|
||||
@@ -49,239 +58,293 @@ def run_cmd(cmd, cwd=None, timeout=None):
|
||||
|
||||
|
||||
def get_current_commit(path):
|
||||
"""Get short hash of current HEAD."""
|
||||
_, commit, _ = run_cmd("git rev-parse --short HEAD", cwd=path)
|
||||
return commit
|
||||
|
||||
|
||||
def get_current_metric(path, metric_grep):
|
||||
"""Read the last recorded metric from results.tsv."""
|
||||
tsv = Path(path) / "results.tsv"
|
||||
def get_best_metric(experiment_dir, direction):
|
||||
"""Read the best metric from results.tsv."""
|
||||
tsv = experiment_dir / "results.tsv"
|
||||
if not tsv.exists():
|
||||
return None
|
||||
lines = [l for l in tsv.read_text().splitlines() if "\tkeep\t" in l]
|
||||
lines = [l for l in tsv.read_text().splitlines()[1:] if "\tkeep\t" in l]
|
||||
if not lines:
|
||||
return None
|
||||
last = lines[-1].split("\t")
|
||||
try:
|
||||
return float(last[1])
|
||||
except (ValueError, IndexError):
|
||||
metrics = []
|
||||
for line in lines:
|
||||
parts = line.split("\t")
|
||||
try:
|
||||
if parts[1] != "N/A":
|
||||
metrics.append(float(parts[1]))
|
||||
except (ValueError, IndexError):
|
||||
continue
|
||||
if not metrics:
|
||||
return None
|
||||
return min(metrics) if direction == "lower" else max(metrics)
|
||||
|
||||
|
||||
def run_evaluation(path, evaluate_cmd, time_budget_minutes):
|
||||
"""Run evaluation with time limit."""
|
||||
hard_limit = time_budget_minutes * 60 * 2.5 # 2.5x as hard timeout
|
||||
def run_evaluation(project_root, eval_cmd, time_budget_minutes, log_file):
|
||||
"""Run evaluation with time limit. Output goes to log_file."""
|
||||
hard_limit = time_budget_minutes * 60 * 2.5
|
||||
t0 = time.time()
|
||||
try:
|
||||
code, _, _ = run_cmd(
|
||||
f"{evaluate_cmd} > run.log 2>&1",
|
||||
cwd=path,
|
||||
f"{eval_cmd} > {log_file} 2>&1",
|
||||
cwd=str(project_root),
|
||||
timeout=hard_limit
|
||||
)
|
||||
elapsed = time.time() - t0
|
||||
return code, elapsed
|
||||
except subprocess.TimeoutExpired:
|
||||
elapsed = time.time() - t0
|
||||
return -1, elapsed # -1 = timeout
|
||||
return -1, elapsed
|
||||
|
||||
|
||||
def extract_metric(path, metric_grep):
|
||||
"""Extract metric value from run.log."""
|
||||
code, out, _ = run_cmd(
|
||||
f"grep '{metric_grep}' run.log | tail -1",
|
||||
cwd=path
|
||||
)
|
||||
if not out:
|
||||
return None
|
||||
try:
|
||||
return float(out.split(":")[-1].strip())
|
||||
except ValueError:
|
||||
def extract_metric(log_file, metric_grep):
|
||||
"""Extract metric value from log file."""
|
||||
log_path = Path(log_file)
|
||||
if not log_path.exists():
|
||||
return None
|
||||
for line in reversed(log_path.read_text().splitlines()):
|
||||
stripped = line.strip()
|
||||
if stripped.startswith(metric_grep.lstrip("^")):
|
||||
try:
|
||||
return float(stripped.split(":")[-1].strip())
|
||||
except ValueError:
|
||||
continue
|
||||
return None
|
||||
|
||||
|
||||
def is_improvement(new_val, old_val, direction):
|
||||
"""Check if new result is better than old."""
|
||||
if old_val is None:
|
||||
return True # First run always "improves"
|
||||
return True
|
||||
if direction == "lower":
|
||||
return new_val < old_val
|
||||
else:
|
||||
return new_val > old_val
|
||||
return new_val > old_val
|
||||
|
||||
|
||||
def log_result(path, commit, metric_val, status, description):
|
||||
def log_result(experiment_dir, commit, metric_val, status, description):
|
||||
"""Append result to results.tsv."""
|
||||
tsv = Path(path) / "results.tsv"
|
||||
tsv = experiment_dir / "results.tsv"
|
||||
metric_str = f"{metric_val:.6f}" if metric_val is not None else "N/A"
|
||||
with open(tsv, "a") as f:
|
||||
f.write(f"{commit}\t{metric_str}\t{status}\t{description}\n")
|
||||
|
||||
|
||||
def get_experiment_count(path):
|
||||
def get_experiment_count(experiment_dir):
|
||||
"""Count experiments run so far."""
|
||||
tsv = Path(path) / "results.tsv"
|
||||
tsv = experiment_dir / "results.tsv"
|
||||
if not tsv.exists():
|
||||
return 0
|
||||
lines = tsv.read_text().splitlines()
|
||||
return max(0, len(lines) - 1) # subtract header
|
||||
return max(0, len(tsv.read_text().splitlines()) - 1)
|
||||
|
||||
|
||||
def run_single_experiment(path, config, exp_num, dry_run=False):
|
||||
def get_last_active(root):
|
||||
"""Find the most recently modified experiment."""
|
||||
latest = None
|
||||
latest_time = 0
|
||||
for domain_dir in root.iterdir():
|
||||
if not domain_dir.is_dir() or domain_dir.name.startswith("."):
|
||||
continue
|
||||
for exp_dir in domain_dir.iterdir():
|
||||
if not exp_dir.is_dir():
|
||||
continue
|
||||
cfg = exp_dir / "config.cfg"
|
||||
if cfg.exists() and cfg.stat().st_mtime > latest_time:
|
||||
latest_time = cfg.stat().st_mtime
|
||||
latest = f"{domain_dir.name}/{exp_dir.name}"
|
||||
return latest
|
||||
|
||||
|
||||
def run_single(project_root, experiment_dir, config, exp_num, dry_run=False):
|
||||
"""Run one experiment iteration."""
|
||||
direction = config.get("metric_direction", "lower")
|
||||
metric_grep = config.get("metric_grep", "^metric:")
|
||||
evaluate_cmd = config.get("evaluate_cmd", "python evaluate.py")
|
||||
eval_cmd = config.get("evaluate_cmd", "python evaluate.py")
|
||||
time_budget = int(config.get("time_budget_minutes", 5))
|
||||
metric_name = config.get("metric", "metric")
|
||||
log_file = str(experiment_dir / "run.log")
|
||||
|
||||
best_so_far = get_current_metric(path, metric_grep)
|
||||
best = get_best_metric(experiment_dir, direction)
|
||||
ts = datetime.now().strftime("%H:%M:%S")
|
||||
|
||||
print(f"\n[{ts}] Experiment #{exp_num}")
|
||||
print(f" Best {metric_name} so far: {best_so_far}")
|
||||
print(f" Best {metric_name}: {best}")
|
||||
|
||||
if dry_run:
|
||||
print(" [DRY RUN] Would run evaluation and check metric")
|
||||
return "dry_run"
|
||||
|
||||
# Save pre-experiment state for rollback
|
||||
code, pre_commit, _ = run_cmd("git rev-parse HEAD", cwd=path)
|
||||
# Save state for rollback
|
||||
code, pre_commit, _ = run_cmd("git rev-parse HEAD", cwd=str(project_root))
|
||||
if code != 0:
|
||||
print(" ✗ Can't get git state. Is this a git repo with commits?")
|
||||
print(" Error: can't get git state")
|
||||
return "error"
|
||||
|
||||
# Run evaluation
|
||||
print(f" Running: {evaluate_cmd} (budget: {time_budget} min)")
|
||||
ret_code, elapsed = run_evaluation(path, evaluate_cmd, time_budget)
|
||||
print(f" Running: {eval_cmd} (budget: {time_budget}m)")
|
||||
ret_code, elapsed = run_evaluation(project_root, eval_cmd, time_budget, log_file)
|
||||
|
||||
# Handle timeout
|
||||
commit = get_current_commit(str(project_root))
|
||||
|
||||
# Timeout
|
||||
if ret_code == -1:
|
||||
print(f" ✗ TIMEOUT after {elapsed:.0f}s — discarding")
|
||||
run_cmd("git checkout -- .", cwd=path) # revert uncommitted changes
|
||||
# Commit was already made by the agent before evaluation
|
||||
run_cmd(f"git reset --hard {pre_commit}", cwd=path)
|
||||
curr_commit = get_current_commit(path)
|
||||
log_result(path, curr_commit, None, "crash", f"timeout after {elapsed:.0f}s")
|
||||
print(f" TIMEOUT after {elapsed:.0f}s — discarding")
|
||||
run_cmd("git checkout -- .", cwd=str(project_root))
|
||||
run_cmd(f"git reset --hard {pre_commit}", cwd=str(project_root))
|
||||
log_result(experiment_dir, commit, None, "crash", f"timeout_{elapsed:.0f}s")
|
||||
return "crash"
|
||||
|
||||
# Handle non-zero exit
|
||||
# Crash
|
||||
if ret_code != 0:
|
||||
# Check if it crashed
|
||||
code, tail, _ = run_cmd("tail -n 5 run.log", cwd=path)
|
||||
print(f" ✗ CRASH (exit {ret_code}) after {elapsed:.0f}s")
|
||||
_, tail, _ = run_cmd(f"tail -5 {log_file}", cwd=str(project_root))
|
||||
print(f" CRASH (exit {ret_code}) after {elapsed:.0f}s")
|
||||
print(f" Last output: {tail[:200]}")
|
||||
run_cmd(f"git reset --hard {pre_commit}", cwd=path)
|
||||
curr_commit = get_current_commit(path)
|
||||
log_result(path, curr_commit, None, "crash", f"exit_code_{ret_code}")
|
||||
run_cmd(f"git reset --hard {pre_commit}", cwd=str(project_root))
|
||||
log_result(experiment_dir, commit, None, "crash", f"exit_{ret_code}")
|
||||
return "crash"
|
||||
|
||||
# Extract metric
|
||||
metric_val = extract_metric(path, metric_grep)
|
||||
metric_val = extract_metric(log_file, metric_grep)
|
||||
if metric_val is None:
|
||||
print(f" ✗ Could not parse metric from run.log")
|
||||
run_cmd(f"git reset --hard {pre_commit}", cwd=path)
|
||||
curr_commit = get_current_commit(path)
|
||||
log_result(path, curr_commit, None, "crash", "metric_parse_failed")
|
||||
print(f" Could not parse {metric_name} from run.log")
|
||||
run_cmd(f"git reset --hard {pre_commit}", cwd=str(project_root))
|
||||
log_result(experiment_dir, commit, None, "crash", "metric_parse_failed")
|
||||
return "crash"
|
||||
|
||||
curr_commit = get_current_commit(path)
|
||||
delta = ""
|
||||
if best_so_far is not None:
|
||||
diff = metric_val - best_so_far
|
||||
delta = f" (Δ{diff:+.4f})"
|
||||
if best is not None:
|
||||
diff = metric_val - best
|
||||
delta = f" (delta {diff:+.4f})"
|
||||
|
||||
print(f" {metric_name}: {metric_val:.6f}{delta} in {elapsed:.0f}s")
|
||||
|
||||
# Keep or discard
|
||||
if is_improvement(metric_val, best_so_far, direction):
|
||||
print(f" ✅ KEEP — improvement confirmed")
|
||||
log_result(path, curr_commit, metric_val, "keep",
|
||||
f"improvement_{metric_name}_{metric_val:.4f}")
|
||||
if is_improvement(metric_val, best, direction):
|
||||
print(f" KEEP — improvement")
|
||||
log_result(experiment_dir, commit, metric_val, "keep",
|
||||
f"improved_{metric_name}_{metric_val:.4f}")
|
||||
return "keep"
|
||||
else:
|
||||
print(f" ❌ DISCARD — no improvement")
|
||||
run_cmd(f"git reset --hard {pre_commit}", cwd=path)
|
||||
curr_commit = get_current_commit(path)
|
||||
log_result(path, curr_commit, metric_val, "discard",
|
||||
f"no_improvement_{metric_val:.4f}_vs_{best_so_far:.4f}")
|
||||
print(f" DISCARD — no improvement")
|
||||
run_cmd(f"git reset --hard {pre_commit}", cwd=str(project_root))
|
||||
best_str = f"{best:.4f}" if best else "?"
|
||||
log_result(experiment_dir, commit, metric_val, "discard",
|
||||
f"no_improvement_{metric_val:.4f}_vs_{best_str}")
|
||||
return "discard"
|
||||
|
||||
|
||||
def print_summary(path):
|
||||
"""Print experiment summary."""
|
||||
tsv = Path(path) / "results.tsv"
|
||||
def print_summary(experiment_dir, config):
|
||||
"""Print session summary."""
|
||||
tsv = experiment_dir / "results.tsv"
|
||||
if not tsv.exists():
|
||||
return
|
||||
lines = tsv.read_text().splitlines()[1:] # skip header
|
||||
lines = tsv.read_text().splitlines()[1:]
|
||||
if not lines:
|
||||
return
|
||||
|
||||
keeps = [l for l in lines if "\tkeep\t" in l]
|
||||
discards = [l for l in lines if "\tdiscard\t" in l]
|
||||
crashes = [l for l in lines if "\tcrash\t" in l]
|
||||
metric_name = config.get("metric", "metric")
|
||||
direction = config.get("metric_direction", "lower")
|
||||
|
||||
print(f"\n{'='*50}")
|
||||
print(f" Session Summary")
|
||||
print(f"\n{'=' * 55}")
|
||||
print(f" autoresearch — Session Summary")
|
||||
print(f" Experiments: {len(lines)} total")
|
||||
print(f" ✅ Keep: {len(keeps)} | ❌ Discard: {len(discards)} | 💥 Crash: {len(crashes)}")
|
||||
print(f" Keep: {len(keeps)} | Discard: {len(discards)} | Crash: {len(crashes)}")
|
||||
|
||||
if keeps:
|
||||
try:
|
||||
first_metric = float(keeps[0].split("\t")[1])
|
||||
last_metric = float(keeps[-1].split("\t")[1])
|
||||
direction = "↓" if last_metric < first_metric else "↑"
|
||||
print(f" Best progress: {first_metric:.6f} → {last_metric:.6f} {direction}")
|
||||
valid = []
|
||||
for l in keeps:
|
||||
parts = l.split("\t")
|
||||
if parts[1] != "N/A":
|
||||
valid.append(float(parts[1]))
|
||||
if len(valid) >= 2:
|
||||
first, last = valid[0], valid[-1]
|
||||
best = min(valid) if direction == "lower" else max(valid)
|
||||
pct = ((first - best) / first * 100) if direction == "lower" else ((best - first) / first * 100)
|
||||
print(f" {metric_name}: {first:.6f} -> {best:.6f} ({pct:+.1f}%)")
|
||||
except (ValueError, IndexError):
|
||||
pass
|
||||
print(f"{'='*50}\n")
|
||||
print(f"{'=' * 55}\n")
|
||||
|
||||
|
||||
def main():
|
||||
parser = argparse.ArgumentParser(description="autoresearch-agent runner")
|
||||
parser.add_argument("--experiment", help="Experiment path: domain/name (e.g. engineering/api-speed)")
|
||||
parser.add_argument("--resume", action="store_true", help="Resume last active experiment")
|
||||
parser.add_argument("--loop", action="store_true", help="Run forever")
|
||||
parser.add_argument("--single", action="store_true", help="Run one experiment")
|
||||
parser.add_argument("--dry-run", action="store_true", help="Dry run only")
|
||||
parser.add_argument("--dry-run", action="store_true", help="Show what would happen")
|
||||
parser.add_argument("--max-experiments", type=int, default=0, help="Max experiments (0 = unlimited)")
|
||||
parser.add_argument("--path", default=".", help="Project root")
|
||||
parser.add_argument("--max-experiments", type=int, default=0,
|
||||
help="Max experiments (0 = unlimited)")
|
||||
args = parser.parse_args()
|
||||
|
||||
path = Path(args.path).resolve()
|
||||
config = load_config(path)
|
||||
project_root = Path(args.path).resolve()
|
||||
root = find_autoresearch_root()
|
||||
|
||||
print(f"\n🔬 autoresearch-agent")
|
||||
print(f" Project: {path}")
|
||||
print(f" Target: {config.get('target', '?')}")
|
||||
print(f" Metric: {config.get('metric', '?')} ({config.get('metric_direction', '?')} is better)")
|
||||
print(f" Budget: {config.get('time_budget_minutes', '?')} min/experiment")
|
||||
print(f" Mode: {'loop' if args.loop else 'single'}")
|
||||
if root is None:
|
||||
print("No .autoresearch/ found. Run setup_experiment.py first.")
|
||||
sys.exit(1)
|
||||
|
||||
if args.single:
|
||||
exp_num = get_experiment_count(path) + 1
|
||||
run_single_experiment(path, config, exp_num, args.dry_run)
|
||||
# Resolve experiment
|
||||
experiment_path = args.experiment
|
||||
if args.resume:
|
||||
experiment_path = get_last_active(root)
|
||||
if not experiment_path:
|
||||
print("No experiments found to resume.")
|
||||
sys.exit(1)
|
||||
print(f"Resuming: {experiment_path}")
|
||||
|
||||
if not experiment_path:
|
||||
print("Specify --experiment domain/name or --resume")
|
||||
sys.exit(1)
|
||||
|
||||
experiment_dir = root / experiment_path
|
||||
if not experiment_dir.exists():
|
||||
print(f"Experiment not found: {experiment_dir}")
|
||||
print("Run: python scripts/setup_experiment.py --list")
|
||||
sys.exit(1)
|
||||
|
||||
config = load_config(experiment_dir)
|
||||
|
||||
domain, name = experiment_path.split("/", 1)
|
||||
print(f"\n autoresearch-agent")
|
||||
print(f" Experiment: {experiment_path}")
|
||||
print(f" Target: {config.get('target', '?')}")
|
||||
print(f" Metric: {config.get('metric', '?')} ({config.get('metric_direction', '?')} is better)")
|
||||
print(f" Budget: {config.get('time_budget_minutes', '?')} min/experiment")
|
||||
print(f" Mode: {'loop' if args.loop else 'single'}")
|
||||
|
||||
if args.single or args.dry_run:
|
||||
exp_num = get_experiment_count(experiment_dir) + 1
|
||||
run_single(project_root, experiment_dir, config, exp_num, args.dry_run)
|
||||
return
|
||||
|
||||
if not args.loop and not args.dry_run:
|
||||
if not args.loop:
|
||||
print("\nSpecify --loop (forever) or --single (one experiment)")
|
||||
sys.exit(1)
|
||||
|
||||
# Setup graceful shutdown
|
||||
# Graceful shutdown
|
||||
def handle_interrupt(sig, frame):
|
||||
print_summary(path)
|
||||
print("\n⏹ Stopped by user.")
|
||||
print_summary(experiment_dir, config)
|
||||
print("\nStopped by user.")
|
||||
sys.exit(0)
|
||||
|
||||
signal.signal(signal.SIGINT, handle_interrupt)
|
||||
signal.signal(signal.SIGTERM, handle_interrupt)
|
||||
|
||||
# Main loop
|
||||
consecutive_crashes = 0
|
||||
exp_num = get_experiment_count(path) + 1
|
||||
exp_num = get_experiment_count(experiment_dir) + 1
|
||||
|
||||
print(f"\nStarting loop. Ctrl+C to stop and print summary.\n")
|
||||
print(f"\nStarting loop. Ctrl+C to stop.\n")
|
||||
|
||||
while True:
|
||||
result = run_single_experiment(path, config, exp_num, args.dry_run)
|
||||
result = run_single(project_root, experiment_dir, config, exp_num, False)
|
||||
exp_num += 1
|
||||
|
||||
if result == "crash":
|
||||
@@ -289,21 +352,16 @@ def main():
|
||||
else:
|
||||
consecutive_crashes = 0
|
||||
|
||||
# Bail if 5 consecutive crashes
|
||||
if consecutive_crashes >= 5:
|
||||
print("\n⚠ 5 consecutive crashes. Pausing for investigation.")
|
||||
print(" Check run.log for the last error.")
|
||||
print("\n 5 consecutive crashes. Pausing.")
|
||||
print(" Check .autoresearch/{}/run.log".format(experiment_path))
|
||||
break
|
||||
|
||||
# Check max experiments
|
||||
if args.max_experiments > 0 and exp_num > args.max_experiments:
|
||||
print(f"\n✓ Reached max experiments ({args.max_experiments})")
|
||||
if 0 < args.max_experiments < exp_num:
|
||||
print(f"\n Reached max experiments ({args.max_experiments})")
|
||||
break
|
||||
|
||||
if args.single:
|
||||
break
|
||||
|
||||
print_summary(path)
|
||||
print_summary(experiment_dir, config)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
@@ -1,65 +1,52 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
autoresearch-agent: Setup Wizard
|
||||
autoresearch-agent: Setup Experiment
|
||||
|
||||
Initializes a new research run:
|
||||
1. Validates the project structure
|
||||
2. Creates a git branch
|
||||
3. Runs the baseline experiment
|
||||
4. Initializes results.tsv
|
||||
Initialize a new experiment with domain, target, evaluator, and git branch.
|
||||
Creates the .autoresearch/{domain}/{name}/ directory structure.
|
||||
|
||||
Usage:
|
||||
python scripts/setup_experiment.py [--config experiment.yaml]
|
||||
python scripts/setup_experiment.py --domain ml|prompt|code|skill
|
||||
python scripts/setup_experiment.py --domain engineering --name api-speed \
|
||||
--target src/api/search.py --eval "pytest bench.py" \
|
||||
--metric p50_ms --direction lower
|
||||
|
||||
python scripts/setup_experiment.py --domain marketing --name medium-ctr \
|
||||
--target content/titles.md --eval "python evaluate.py" \
|
||||
--metric ctr_score --direction higher --evaluator llm_judge_content
|
||||
|
||||
python scripts/setup_experiment.py --list # List all experiments
|
||||
python scripts/setup_experiment.py --list-evaluators # List available evaluators
|
||||
"""
|
||||
|
||||
import argparse
|
||||
import os
|
||||
import shutil
|
||||
import subprocess
|
||||
import sys
|
||||
import time
|
||||
from datetime import datetime
|
||||
from pathlib import Path
|
||||
|
||||
DOMAINS = ["engineering", "marketing", "content", "prompts", "custom"]
|
||||
|
||||
DOMAINS = {
|
||||
"ml": {
|
||||
"target": "train.py",
|
||||
"evaluate_cmd": "uv run train.py",
|
||||
"metric": "val_bpb",
|
||||
"metric_direction": "lower",
|
||||
"time_budget_minutes": 5,
|
||||
"metric_grep": "^val_bpb:",
|
||||
},
|
||||
"prompt": {
|
||||
"target": "prompt.md",
|
||||
"evaluate_cmd": "python evaluate.py",
|
||||
"metric": "eval_score",
|
||||
"metric_direction": "higher",
|
||||
"time_budget_minutes": 2,
|
||||
"metric_grep": "^eval_score:",
|
||||
},
|
||||
"code": {
|
||||
"target": "src/module.py",
|
||||
"evaluate_cmd": "python benchmark.py",
|
||||
"metric": "p50_ms",
|
||||
"metric_direction": "lower",
|
||||
"time_budget_minutes": 10,
|
||||
"metric_grep": "^p50_ms:",
|
||||
},
|
||||
"skill": {
|
||||
"target": "SKILL.md",
|
||||
"evaluate_cmd": "python scripts/skill_evaluator.py",
|
||||
"metric": "pass_rate",
|
||||
"metric_direction": "higher",
|
||||
"time_budget_minutes": 5,
|
||||
"metric_grep": "^pass_rate:",
|
||||
},
|
||||
}
|
||||
EVALUATOR_DIR = Path(__file__).parent.parent / "evaluators"
|
||||
|
||||
DEFAULT_CONFIG = """# autoresearch global config
|
||||
default_time_budget_minutes: 5
|
||||
default_scope: project
|
||||
dashboard_format: markdown
|
||||
"""
|
||||
|
||||
GITIGNORE_CONTENT = """# autoresearch — experiment logs are local state
|
||||
**/results.tsv
|
||||
**/run.log
|
||||
**/run.*.log
|
||||
config.yaml
|
||||
"""
|
||||
|
||||
|
||||
def run_cmd(cmd, cwd=None, timeout=None):
|
||||
"""Run a shell command and return (returncode, stdout, stderr)."""
|
||||
"""Run shell command, return (returncode, stdout, stderr)."""
|
||||
result = subprocess.run(
|
||||
cmd, shell=True, capture_output=True, text=True,
|
||||
cwd=cwd, timeout=timeout
|
||||
@@ -67,188 +54,315 @@ def run_cmd(cmd, cwd=None, timeout=None):
|
||||
return result.returncode, result.stdout.strip(), result.stderr.strip()
|
||||
|
||||
|
||||
def check_git_repo(path):
|
||||
"""Verify we're in a git repo."""
|
||||
code, out, err = run_cmd("git rev-parse --is-inside-work-tree", cwd=path)
|
||||
if code != 0:
|
||||
print("✗ Not a git repository. Run: git init && git add . && git commit -m 'initial'")
|
||||
def get_autoresearch_root(scope, project_root=None):
|
||||
"""Get the .autoresearch root directory based on scope."""
|
||||
if scope == "user":
|
||||
return Path.home() / ".autoresearch"
|
||||
return Path(project_root or ".") / ".autoresearch"
|
||||
|
||||
|
||||
def init_root(root):
|
||||
"""Initialize .autoresearch root if it doesn't exist."""
|
||||
created = False
|
||||
if not root.exists():
|
||||
root.mkdir(parents=True)
|
||||
created = True
|
||||
print(f" Created {root}/")
|
||||
|
||||
config_file = root / "config.yaml"
|
||||
if not config_file.exists():
|
||||
config_file.write_text(DEFAULT_CONFIG)
|
||||
print(f" Created {config_file}")
|
||||
|
||||
gitignore = root / ".gitignore"
|
||||
if not gitignore.exists():
|
||||
gitignore.write_text(GITIGNORE_CONTENT)
|
||||
print(f" Created {gitignore}")
|
||||
|
||||
return created
|
||||
|
||||
|
||||
def create_program_md(experiment_dir, domain, name, target, metric, direction, constraints=""):
|
||||
"""Generate a program.md template for the experiment."""
|
||||
direction_word = "Minimize" if direction == "lower" else "Maximize"
|
||||
content = f"""# autoresearch — {name}
|
||||
|
||||
## Goal
|
||||
{direction_word} `{metric}` on `{target}`. {"Lower" if direction == "lower" else "Higher"} is better.
|
||||
|
||||
## What the Agent Can Change
|
||||
- Only `{target}` — this is the single file being optimized.
|
||||
- Everything inside that file is fair game unless constrained below.
|
||||
|
||||
## What the Agent Cannot Change
|
||||
- The evaluation script (`evaluate.py` or the eval command). It is read-only.
|
||||
- Dependencies — do not add new packages or imports that aren't already available.
|
||||
- Any other files in the project unless explicitly noted here.
|
||||
{f"- Additional constraints: {constraints}" if constraints else ""}
|
||||
|
||||
## Strategy
|
||||
1. First run: establish baseline. Do not change anything.
|
||||
2. Profile/analyze the current state — understand why the metric is what it is.
|
||||
3. Try the most obvious improvement first (low-hanging fruit).
|
||||
4. If that works, push further in the same direction.
|
||||
5. If stuck, try something orthogonal or radical.
|
||||
6. Read the git log of previous experiments. Don't repeat failed approaches.
|
||||
|
||||
## Simplicity Rule
|
||||
A small improvement that adds ugly complexity is NOT worth it.
|
||||
Equal performance with simpler code IS worth it.
|
||||
Removing code that gets same results is the best outcome.
|
||||
|
||||
## Stop When
|
||||
You don't stop. The human will interrupt you when they're satisfied.
|
||||
If no improvement in 20+ consecutive runs, change strategy drastically.
|
||||
"""
|
||||
(experiment_dir / "program.md").write_text(content)
|
||||
|
||||
|
||||
def create_config(experiment_dir, target, eval_cmd, metric, direction, time_budget):
|
||||
"""Write experiment config."""
|
||||
content = f"""target: {target}
|
||||
evaluate_cmd: {eval_cmd}
|
||||
metric: {metric}
|
||||
metric_direction: {direction}
|
||||
metric_grep: ^{metric}:
|
||||
time_budget_minutes: {time_budget}
|
||||
created: {datetime.now().strftime('%Y-%m-%d %H:%M')}
|
||||
"""
|
||||
(experiment_dir / "config.cfg").write_text(content)
|
||||
|
||||
|
||||
def init_results_tsv(experiment_dir):
|
||||
"""Create results.tsv with header."""
|
||||
tsv = experiment_dir / "results.tsv"
|
||||
if tsv.exists():
|
||||
print(f" results.tsv already exists ({tsv.stat().st_size} bytes)")
|
||||
return
|
||||
tsv.write_text("commit\tmetric\tstatus\tdescription\n")
|
||||
print(" Created results.tsv")
|
||||
|
||||
|
||||
def copy_evaluator(experiment_dir, evaluator_name):
|
||||
"""Copy a built-in evaluator to the experiment directory."""
|
||||
source = EVALUATOR_DIR / f"{evaluator_name}.py"
|
||||
if not source.exists():
|
||||
print(f" Warning: evaluator '{evaluator_name}' not found in {EVALUATOR_DIR}")
|
||||
print(f" Available: {', '.join(f.stem for f in EVALUATOR_DIR.glob('*.py'))}")
|
||||
return False
|
||||
print("✓ Git repository found")
|
||||
dest = experiment_dir / "evaluate.py"
|
||||
shutil.copy2(source, dest)
|
||||
print(f" Copied evaluator: {evaluator_name}.py -> evaluate.py")
|
||||
return True
|
||||
|
||||
|
||||
def check_program_md(path):
|
||||
"""Check program.md exists and has content."""
|
||||
pm = Path(path) / "program.md"
|
||||
if not pm.exists():
|
||||
print("⚠ program.md not found. Creating template...")
|
||||
return False
|
||||
content = pm.read_text()
|
||||
if len(content) < 100:
|
||||
print("⚠ program.md looks empty. Fill it out before running experiments.")
|
||||
return False
|
||||
print(f"✓ program.md found ({len(content)} chars)")
|
||||
return True
|
||||
|
||||
|
||||
def check_target_file(path, target):
|
||||
"""Check target file exists."""
|
||||
tf = Path(path) / target
|
||||
if not tf.exists():
|
||||
print(f"✗ Target file not found: {target}")
|
||||
return False
|
||||
print(f"✓ Target file found: {target}")
|
||||
return True
|
||||
|
||||
|
||||
def check_evaluate_script(path):
|
||||
"""Check evaluate.py exists."""
|
||||
ev = Path(path) / "evaluate.py"
|
||||
if not ev.exists():
|
||||
print("⚠ evaluate.py not found. You need a fixed evaluation function.")
|
||||
print(" Create evaluate.py that outputs: metric_name: <value>")
|
||||
return False
|
||||
print("✓ evaluate.py found")
|
||||
return True
|
||||
|
||||
|
||||
def create_branch(path, tag):
|
||||
def create_branch(path, domain, name):
|
||||
"""Create and checkout the experiment branch."""
|
||||
branch = f"autoresearch/{tag}"
|
||||
code, out, err = run_cmd(f"git checkout -b {branch}", cwd=path)
|
||||
branch = f"autoresearch/{domain}/{name}"
|
||||
code, _, err = run_cmd(f"git checkout -b {branch}", cwd=path)
|
||||
if code != 0:
|
||||
if "already exists" in err:
|
||||
print(f"✗ Branch '{branch}' already exists. Use a different tag.")
|
||||
else:
|
||||
print(f"✗ Failed to create branch: {err}")
|
||||
print(f" Branch '{branch}' already exists. Checking out...")
|
||||
run_cmd(f"git checkout {branch}", cwd=path)
|
||||
return branch
|
||||
print(f" Warning: could not create branch: {err}")
|
||||
return None
|
||||
print(f"✓ Created branch: {branch}")
|
||||
print(f" Created branch: {branch}")
|
||||
return branch
|
||||
|
||||
|
||||
def init_results_tsv(path):
|
||||
"""Create results.tsv with header."""
|
||||
tsv = Path(path) / "results.tsv"
|
||||
if tsv.exists():
|
||||
print(f"✓ results.tsv already exists ({tsv.stat().st_size} bytes)")
|
||||
def list_experiments(root):
|
||||
"""List all experiments across all domains."""
|
||||
if not root.exists():
|
||||
print("No experiments found. Run setup to create your first experiment.")
|
||||
return
|
||||
tsv.write_text("commit\tmetric\tstatus\tdescription\n")
|
||||
print("✓ Created results.tsv")
|
||||
|
||||
experiments = []
|
||||
for domain_dir in sorted(root.iterdir()):
|
||||
if not domain_dir.is_dir() or domain_dir.name.startswith("."):
|
||||
continue
|
||||
for exp_dir in sorted(domain_dir.iterdir()):
|
||||
if not exp_dir.is_dir():
|
||||
continue
|
||||
cfg_file = exp_dir / "config.cfg"
|
||||
if not cfg_file.exists():
|
||||
continue
|
||||
config = {}
|
||||
for line in cfg_file.read_text().splitlines():
|
||||
if ":" in line:
|
||||
k, v = line.split(":", 1)
|
||||
config[k.strip()] = v.strip()
|
||||
|
||||
# Count results
|
||||
tsv = exp_dir / "results.tsv"
|
||||
runs = 0
|
||||
if tsv.exists():
|
||||
runs = max(0, len(tsv.read_text().splitlines()) - 1)
|
||||
|
||||
experiments.append({
|
||||
"domain": domain_dir.name,
|
||||
"name": exp_dir.name,
|
||||
"target": config.get("target", "?"),
|
||||
"metric": config.get("metric", "?"),
|
||||
"runs": runs,
|
||||
})
|
||||
|
||||
if not experiments:
|
||||
print("No experiments found.")
|
||||
return
|
||||
|
||||
print(f"\n{'DOMAIN':<15} {'EXPERIMENT':<25} {'TARGET':<30} {'METRIC':<15} {'RUNS':>5}")
|
||||
print("-" * 95)
|
||||
for e in experiments:
|
||||
print(f"{e['domain']:<15} {e['name']:<25} {e['target']:<30} {e['metric']:<15} {e['runs']:>5}")
|
||||
print(f"\nTotal: {len(experiments)} experiments")
|
||||
|
||||
|
||||
def run_baseline(path, evaluate_cmd, metric_grep, time_budget_minutes):
|
||||
"""Run the baseline experiment."""
|
||||
print(f"\nRunning baseline experiment (~{time_budget_minutes} min)...")
|
||||
timeout = time_budget_minutes * 60 * 2.5 # 2.5x budget as hard limit
|
||||
def list_evaluators():
|
||||
"""List available built-in evaluators."""
|
||||
if not EVALUATOR_DIR.exists():
|
||||
print("No evaluators directory found.")
|
||||
return
|
||||
|
||||
t0 = time.time()
|
||||
code, out, err = run_cmd(
|
||||
f"{evaluate_cmd} > run.log 2>&1",
|
||||
cwd=path,
|
||||
timeout=timeout
|
||||
)
|
||||
elapsed = time.time() - t0
|
||||
|
||||
if code != 0:
|
||||
print(f"✗ Baseline run failed after {elapsed:.0f}s. Check run.log")
|
||||
return None
|
||||
|
||||
# Extract metric
|
||||
grep_code, grep_out, _ = run_cmd(
|
||||
f"grep '{metric_grep}' run.log | tail -1",
|
||||
cwd=path
|
||||
)
|
||||
if not grep_out:
|
||||
print("✗ Could not extract metric from run.log. Check metric_grep pattern.")
|
||||
return None
|
||||
|
||||
metric_value = grep_out.split(":")[-1].strip()
|
||||
print(f"✓ Baseline complete in {elapsed:.0f}s — metric: {metric_value}")
|
||||
return metric_value
|
||||
print(f"\nAvailable evaluators ({EVALUATOR_DIR}):\n")
|
||||
for f in sorted(EVALUATOR_DIR.glob("*.py")):
|
||||
# Read first docstring line
|
||||
desc = ""
|
||||
for line in f.read_text().splitlines():
|
||||
if line.strip().startswith('"""') or line.strip().startswith("'''"):
|
||||
continue
|
||||
if line.strip() and not line.startswith("#!"):
|
||||
desc = line.strip().strip('"').strip("'")
|
||||
break
|
||||
print(f" {f.stem:<25} {desc}")
|
||||
|
||||
|
||||
def main():
|
||||
parser = argparse.ArgumentParser(description="autoresearch-agent setup")
|
||||
parser.add_argument("--domain", choices=list(DOMAINS.keys()), help="Experiment domain")
|
||||
parser.add_argument("--domain", choices=DOMAINS, help="Experiment domain")
|
||||
parser.add_argument("--name", help="Experiment name (e.g. api-speed, medium-ctr)")
|
||||
parser.add_argument("--target", help="Target file to optimize")
|
||||
parser.add_argument("--evaluate-cmd", help="Evaluation command")
|
||||
parser.add_argument("--metric", help="Metric name")
|
||||
parser.add_argument("--direction", choices=["lower", "higher"], default="lower")
|
||||
parser.add_argument("--budget", type=int, default=5, help="Time budget in minutes")
|
||||
parser.add_argument("--tag", help="Run tag (used in branch name)")
|
||||
parser.add_argument("--eval", dest="eval_cmd", help="Evaluation command")
|
||||
parser.add_argument("--metric", help="Metric name (must appear in eval output as 'name: value')")
|
||||
parser.add_argument("--direction", choices=["lower", "higher"], default="lower",
|
||||
help="Is lower or higher better?")
|
||||
parser.add_argument("--time-budget", type=int, default=5, help="Minutes per experiment (default: 5)")
|
||||
parser.add_argument("--evaluator", help="Built-in evaluator to copy (e.g. benchmark_speed)")
|
||||
parser.add_argument("--scope", choices=["project", "user"], default="project",
|
||||
help="Where to store experiments: project (./) or user (~/)")
|
||||
parser.add_argument("--constraints", default="", help="Additional constraints for program.md")
|
||||
parser.add_argument("--path", default=".", help="Project root path")
|
||||
parser.add_argument("--skip-baseline", action="store_true")
|
||||
parser.add_argument("--skip-baseline", action="store_true", help="Skip baseline run")
|
||||
parser.add_argument("--skip-branch", action="store_true", help="Don't create git branch")
|
||||
parser.add_argument("--list", action="store_true", help="List all experiments")
|
||||
parser.add_argument("--list-evaluators", action="store_true", help="List available evaluators")
|
||||
args = parser.parse_args()
|
||||
|
||||
path = Path(args.path).resolve()
|
||||
print(f"\n🔬 autoresearch-agent setup")
|
||||
print(f" Project: {path}")
|
||||
print(f" Time: {datetime.now().strftime('%Y-%m-%d %H:%M')}\n")
|
||||
project_root = Path(args.path).resolve()
|
||||
|
||||
# Get config from domain or args
|
||||
if args.domain:
|
||||
config = DOMAINS[args.domain].copy()
|
||||
# List mode
|
||||
if args.list:
|
||||
root = get_autoresearch_root("project", project_root)
|
||||
list_experiments(root)
|
||||
user_root = get_autoresearch_root("user")
|
||||
if user_root.exists() and user_root != root:
|
||||
print(f"\n--- User-level experiments ({user_root}) ---")
|
||||
list_experiments(user_root)
|
||||
return
|
||||
|
||||
if args.list_evaluators:
|
||||
list_evaluators()
|
||||
return
|
||||
|
||||
# Validate required args for setup
|
||||
if not all([args.domain, args.name, args.target, args.eval_cmd, args.metric]):
|
||||
parser.error("Required: --domain, --name, --target, --eval, --metric")
|
||||
|
||||
root = get_autoresearch_root(args.scope, project_root)
|
||||
|
||||
print(f"\n autoresearch-agent setup")
|
||||
print(f" Project: {project_root}")
|
||||
print(f" Scope: {args.scope}")
|
||||
print(f" Domain: {args.domain}")
|
||||
print(f" Experiment: {args.name}")
|
||||
print(f" Time: {datetime.now().strftime('%Y-%m-%d %H:%M')}\n")
|
||||
|
||||
# Check git
|
||||
code, _, _ = run_cmd("git rev-parse --is-inside-work-tree", cwd=str(project_root))
|
||||
if code != 0:
|
||||
print(" Error: not a git repository. Run: git init && git add . && git commit -m 'initial'")
|
||||
sys.exit(1)
|
||||
print(" Git repository found")
|
||||
|
||||
# Check target file
|
||||
target_path = project_root / args.target
|
||||
if not target_path.exists():
|
||||
print(f" Error: target file not found: {args.target}")
|
||||
sys.exit(1)
|
||||
print(f" Target file found: {args.target}")
|
||||
|
||||
# Init root
|
||||
init_root(root)
|
||||
|
||||
# Create experiment directory
|
||||
experiment_dir = root / args.domain / args.name
|
||||
if experiment_dir.exists():
|
||||
print(f" Warning: experiment '{args.domain}/{args.name}' already exists.")
|
||||
print(f" Use --name with a different name, or delete {experiment_dir}")
|
||||
sys.exit(1)
|
||||
experiment_dir.mkdir(parents=True)
|
||||
print(f" Created {experiment_dir}/")
|
||||
|
||||
# Create files
|
||||
create_program_md(experiment_dir, args.domain, args.name,
|
||||
args.target, args.metric, args.direction, args.constraints)
|
||||
print(" Created program.md")
|
||||
|
||||
create_config(experiment_dir, args.target, args.eval_cmd,
|
||||
args.metric, args.direction, args.time_budget)
|
||||
print(" Created config.cfg")
|
||||
|
||||
init_results_tsv(experiment_dir)
|
||||
|
||||
# Copy evaluator if specified
|
||||
if args.evaluator:
|
||||
copy_evaluator(experiment_dir, args.evaluator)
|
||||
|
||||
# Create git branch
|
||||
if not args.skip_branch:
|
||||
create_branch(str(project_root), args.domain, args.name)
|
||||
|
||||
# Test evaluation command
|
||||
print(f"\n Testing evaluation: {args.eval_cmd}")
|
||||
code, out, err = run_cmd(args.eval_cmd, cwd=str(project_root), timeout=60)
|
||||
if code != 0:
|
||||
print(f" Warning: eval command failed (exit {code})")
|
||||
if err:
|
||||
print(f" stderr: {err[:200]}")
|
||||
print(" Fix the eval command before running the experiment loop.")
|
||||
else:
|
||||
config = {
|
||||
"target": args.target or "target.py",
|
||||
"evaluate_cmd": args.evaluate_cmd or "python evaluate.py",
|
||||
"metric": args.metric or "score",
|
||||
"metric_direction": args.direction,
|
||||
"time_budget_minutes": args.budget,
|
||||
"metric_grep": f"^{args.metric or 'score'}:",
|
||||
}
|
||||
# Check metric is parseable
|
||||
full_output = out + "\n" + err
|
||||
metric_found = False
|
||||
for line in full_output.splitlines():
|
||||
if line.strip().startswith(f"{args.metric}:"):
|
||||
metric_found = True
|
||||
print(f" Eval works. Baseline: {line.strip()}")
|
||||
break
|
||||
if not metric_found:
|
||||
print(f" Warning: eval ran but '{args.metric}:' not found in output.")
|
||||
print(f" Make sure your eval command outputs: {args.metric}: <value>")
|
||||
|
||||
tag = args.tag or datetime.now().strftime("%b%d").lower()
|
||||
|
||||
# Validation checks
|
||||
checks = [
|
||||
check_git_repo(path),
|
||||
check_program_md(path),
|
||||
check_target_file(path, config["target"]),
|
||||
check_evaluate_script(path),
|
||||
]
|
||||
|
||||
if not all(checks):
|
||||
print("\n⚠ Fix the above issues before running experiments.")
|
||||
sys.exit(1)
|
||||
|
||||
# Create branch
|
||||
branch = create_branch(path, tag)
|
||||
if not branch:
|
||||
sys.exit(1)
|
||||
|
||||
# Init results TSV
|
||||
init_results_tsv(path)
|
||||
|
||||
# Save config for run_experiment.py
|
||||
config_content = "\n".join(f"{k}: {v}" for k, v in config.items())
|
||||
(path / ".autoresearch.cfg").write_text(config_content + "\n")
|
||||
print("✓ Saved .autoresearch.cfg")
|
||||
|
||||
# Run baseline
|
||||
if not args.skip_baseline:
|
||||
baseline = run_baseline(
|
||||
path,
|
||||
config["evaluate_cmd"],
|
||||
config["metric_grep"],
|
||||
config["time_budget_minutes"]
|
||||
)
|
||||
if baseline:
|
||||
# Log baseline to TSV
|
||||
code, commit, _ = run_cmd("git rev-parse --short HEAD", cwd=path)
|
||||
with open(path / "results.tsv", "a") as f:
|
||||
f.write(f"{commit}\t{baseline}\tkeep\tbaseline\n")
|
||||
print(f"✓ Baseline logged to results.tsv")
|
||||
|
||||
print(f"\n✅ Setup complete!")
|
||||
print(f" Branch: {branch}")
|
||||
print(f" Target: {config['target']}")
|
||||
print(f" Metric: {config['metric']} ({config['metric_direction']} is better)")
|
||||
print(f" Budget: {config['time_budget_minutes']} min/experiment")
|
||||
print(f"\nTo start the autonomous loop:")
|
||||
print(f" python scripts/run_experiment.py --loop")
|
||||
print(f"\nOr run a single experiment:")
|
||||
print(f" python scripts/run_experiment.py --single")
|
||||
# Summary
|
||||
print(f"\n Setup complete!")
|
||||
print(f" Experiment: {args.domain}/{args.name}")
|
||||
print(f" Target: {args.target}")
|
||||
print(f" Metric: {args.metric} ({args.direction} is better)")
|
||||
print(f" Budget: {args.time_budget} min/experiment")
|
||||
if not args.skip_branch:
|
||||
print(f" Branch: autoresearch/{args.domain}/{args.name}")
|
||||
print(f"\n To start:")
|
||||
print(f" python scripts/run_experiment.py --experiment {args.domain}/{args.name} --loop")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
Reference in New Issue
Block a user