Autoresearch Agent

#!/usr/bin/env python3
"""
autoresearch-agent: Results Viewer

View experiment results in multiple formats: terminal, CSV, Markdown.
Supports single experiment, domain, or cross-experiment dashboard.

Usage:
    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
import time
from pathlib import Path


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 []
    results = []
    for line in tsv.read_text().splitlines()[1:]:
        parts = line.split("\t")
        if len(parts) >= 4:
            try:
                metric = float(parts[1]) if parts[1] != "N/A" else None
            except ValueError:
                metric = None
            results.append({
                "commit": parts[0],
                "metric": metric,
                "status": parts[2],
                "description": parts[3],
            })
    return results


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"]

    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

    pct_change = None
    if baseline is not None and best is not None and baseline != 0:
        if direction == "lower":
            pct_change = (baseline - best) / baseline * 100
        else:
            pct_change = (best - baseline) / baseline * 100

    return {
        "total": len(results),
        "keeps": len(keeps),
        "discards": len(discards),
        "crashes": len(crashes),
        "baseline": baseline,
        "best": best,
        "pct_change": pct_change,
    }


# --- 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(f"No results for {experiment_path}")
        return

    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)

            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 "—"

            # Determine status
            status = "idle"
            if stats["total"] > 0:
                tsv = exp_dir / "results.tsv"
                if tsv.exists():
                    age_hours = (time.time() - tsv.stat().st_mtime) / 3600
                    status = "active" if age_hours < 1 else "paused" if age_hours < 24 else "done"

            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"] is not None 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, domain_filter=None):
    """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
        if domain_filter and domain_dir.name != domain_filter:
            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"] is not None else ""
            pct_str = f"{stats['pct_change']:+.1f}%" if stats["pct_change"] is not None 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"] is not None 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, domain_filter=None):
    """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
        if domain_filter and domain_dir.name != domain_filter:
            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"] is not None else "—"
            pct = f"{stats['pct_change']:+.1f}%" if stats["pct_change"] is not None else "—"

            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(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()

    root = find_autoresearch_root()
    if root is None:
        print("No .autoresearch/ found. Run setup_experiment.py first.")
        sys.exit(1)

    output_text = None

    # 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.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

    # 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, domain_filter=args.domain) if args.format == "csv" else export_dashboard_markdown(root, domain_filter=args.domain)
        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:
        # 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__":
    main()

#!/usr/bin/env python3
"""
autoresearch-agent: Experiment Runner

Executes a single experiment iteration. The AI agent is the loop —
it calls this script repeatedly. The script handles evaluation,
metric parsing, keep/discard decisions, and git rollback on failure.

Usage:
    python scripts/run_experiment.py --experiment engineering/api-speed --single
    python scripts/run_experiment.py --experiment engineering/api-speed --dry-run
    python scripts/run_experiment.py --experiment engineering/api-speed --single --description "added caching"
"""

import argparse
import subprocess
import sys
import time
from datetime import datetime
from pathlib import Path


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(f"  Error: no config.cfg in {experiment_dir}")
        sys.exit(1)
    config = {}
    for line in cfg_file.read_text().splitlines():
        if ":" in line:
            k, v = line.split(":", 1)
            config[k.strip()] = v.strip()
    return config


def run_git(args, cwd=None, timeout=30):
    """Run a git command safely (no shell injection). Returns (returncode, stdout, stderr)."""
    result = subprocess.run(
        ["git"] + args,
        capture_output=True, text=True,
        cwd=cwd, timeout=timeout
    )
    return result.returncode, result.stdout.strip(), result.stderr.strip()


def get_current_commit(path):
    """Get short hash of current HEAD."""
    _, commit, _ = run_git(["rev-parse", "--short", "HEAD"], cwd=path)
    return commit


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()[1:] if "\tkeep\t" in l]
    if not lines:
        return None
    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(project_root, eval_cmd, time_budget_minutes, log_file):
    """Run evaluation with time limit. Output goes to log_file.

    Note: shell=True is intentional here — eval_cmd is user-provided and
    may contain pipes, redirects, or chained commands.
    """
    hard_limit = time_budget_minutes * 60 * 2.5
    t0 = time.time()
    try:
        with open(log_file, "w") as lf:
            result = subprocess.run(
                eval_cmd, shell=True,
                stdout=lf, stderr=subprocess.STDOUT,
                cwd=str(project_root),
                timeout=hard_limit
            )
        elapsed = time.time() - t0
        return result.returncode, elapsed
    except subprocess.TimeoutExpired:
        elapsed = time.time() - t0
        return -1, elapsed


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
    if direction == "lower":
        return new_val < old_val
    return new_val > old_val


def log_result(experiment_dir, commit, metric_val, status, description):
    """Append result to 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(experiment_dir):
    """Count experiments run so far."""
    tsv = experiment_dir / "results.tsv"
    if not tsv.exists():
        return 0
    return max(0, len(tsv.read_text().splitlines()) - 1)


def get_description_from_diff(project_root):
    """Auto-generate a description from git diff --stat HEAD~1."""
    code, diff_stat, _ = run_git(["diff", "--stat", "HEAD~1"], cwd=str(project_root))
    if code == 0 and diff_stat:
        return diff_stat.split("\n")[0][:50]
    return "experiment"


def read_last_lines(filepath, n=5):
    """Read last n lines of a file (replaces tail shell command)."""
    path = Path(filepath)
    if not path.exists():
        return ""
    lines = path.read_text().splitlines()
    return "\n".join(lines[-n:])


def run_single(project_root, experiment_dir, config, exp_num, dry_run=False, description=None):
    """Run one experiment iteration."""
    direction = config.get("metric_direction", "lower")
    metric_grep = config.get("metric_grep", "^metric:")
    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 = 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}: {best}")

    if dry_run:
        print("  [DRY RUN] Would run evaluation and check metric")
        return "dry_run"

    # Auto-generate description if not provided
    if not description:
        description = get_description_from_diff(str(project_root))

    # Run evaluation
    print(f"  Running: {eval_cmd} (budget: {time_budget}m)")
    ret_code, elapsed = run_evaluation(project_root, eval_cmd, time_budget, log_file)

    commit = get_current_commit(str(project_root))

    # Timeout
    if ret_code == -1:
        print(f"  TIMEOUT after {elapsed:.0f}s — discarding")
        run_git(["checkout", "--", "."], cwd=str(project_root))
        run_git(["reset", "--hard", "HEAD~1"], cwd=str(project_root))
        log_result(experiment_dir, commit, None, "crash", f"timeout_{elapsed:.0f}s")
        return "crash"

    # Crash
    if ret_code != 0:
        tail = read_last_lines(log_file, 5)
        print(f"  CRASH (exit {ret_code}) after {elapsed:.0f}s")
        print(f"  Last output: {tail[:200]}")
        run_git(["reset", "--hard", "HEAD~1"], cwd=str(project_root))
        log_result(experiment_dir, commit, None, "crash", f"exit_{ret_code}")
        return "crash"

    # Extract metric
    metric_val = extract_metric(log_file, metric_grep)
    if metric_val is None:
        print(f"  Could not parse {metric_name} from run.log")
        run_git(["reset", "--hard", "HEAD~1"], cwd=str(project_root))
        log_result(experiment_dir, commit, None, "crash", "metric_parse_failed")
        return "crash"

    delta = ""
    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, direction):
        print(f"  KEEP — improvement")
        log_result(experiment_dir, commit, metric_val, "keep", description)
        return "keep"
    else:
        print(f"  DISCARD — no improvement")
        run_git(["reset", "--hard", "HEAD~1"], cwd=str(project_root))
        best_str = f"{best:.4f}" if best is not None else "?"
        log_result(experiment_dir, commit, metric_val, "discard",
                   f"no_improvement_{metric_val:.4f}_vs_{best_str}")
        return "discard"


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("--single", action="store_true", help="Run one experiment iteration")
    parser.add_argument("--dry-run", action="store_true", help="Show what would happen")
    parser.add_argument("--description", help="Description of the change (auto-generated from git diff if omitted)")
    parser.add_argument("--path", default=".", help="Project root")
    args = parser.parse_args()

    project_root = 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 not args.experiment:
        print("Specify --experiment domain/name")
        sys.exit(1)

    experiment_dir = root / args.experiment
    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)

    print(f"\n  autoresearch-agent")
    print(f"  Experiment: {args.experiment}")
    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: {'dry-run' if args.dry_run else 'single'}")

    exp_num = get_experiment_count(experiment_dir) + 1
    run_single(project_root, experiment_dir, config, exp_num, args.dry_run, args.description)


if __name__ == "__main__":
    main()

#!/usr/bin/env python3
"""
autoresearch-agent: Setup Experiment

Initialize a new experiment with domain, target, evaluator, and git branch.
Creates the .autoresearch/{domain}/{name}/ directory structure.

Usage:
    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 shutil
import subprocess
import sys
from datetime import datetime
from pathlib import Path

DOMAINS = ["engineering", "marketing", "content", "prompts", "custom"]

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 shell command, return (returncode, stdout, stderr)."""
    result = subprocess.run(
        cmd, shell=True, capture_output=True, text=True,
        cwd=cwd, timeout=timeout
    )
    return result.returncode, result.stdout.strip(), result.stderr.strip()


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
    dest = experiment_dir / "evaluate.py"
    shutil.copy2(source, dest)
    print(f"  Copied evaluator: {evaluator_name}.py -> evaluate.py")
    return True


def create_branch(path, domain, name):
    """Create and checkout the experiment branch."""
    branch = f"autoresearch/{domain}/{name}"
    result = subprocess.run(
        ["git", "checkout", "-b", branch],
        cwd=path, capture_output=True, text=True
    )
    if result.returncode != 0:
        if "already exists" in result.stderr:
            print(f"  Branch '{branch}' already exists. Checking out...")
            subprocess.run(
                ["git", "checkout", branch],
                cwd=path, capture_output=True, text=True
            )
            return branch
        print(f"  Warning: could not create branch: {result.stderr}")
        return None
    print(f"  Created branch: {branch}")
    return branch


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

    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 list_evaluators():
    """List available built-in evaluators."""
    if not EVALUATOR_DIR.exists():
        print("No evaluators directory found.")
        return

    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():
            stripped = line.strip()
            if stripped.startswith('"""') or stripped.startswith("'''"):
                quote = stripped[:3]
                # Single-line docstring: """Description."""
                after_quote = stripped[3:]
                if after_quote and after_quote.rstrip(quote[0]).strip():
                    desc = after_quote.rstrip('"').rstrip("'").strip()
                    break
                continue
            if stripped and not line.startswith("#!"):
                desc = stripped.strip('"').strip("'")
                break
        print(f"  {f.stem:<25} {desc}")


def main():
    parser = argparse.ArgumentParser(description="autoresearch-agent setup")
    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("--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-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()

    project_root = Path(args.path).resolve()

    # 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
    result = subprocess.run(
        ["git", "rev-parse", "--is-inside-work-tree"],
        cwd=str(project_root), capture_output=True, text=True
    )
    code = result.returncode
    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:
        # 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>")

    # 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} --single")


if __name__ == "__main__":
    main()