markitect-main/markitect/infospace/cli.py

"""
CLI commands for infospace lifecycle management.

Provides ``markitect infospace`` subcommands for initialising,
inspecting, and evaluating infospaces.
"""

from __future__ import annotations

from pathlib import Path
from typing import Optional

import click

from markitect.infospace.config import (
    DisciplineBinding,
    InfospaceConfig,
    SchemaRegistry,
    TopicConfig,
    find_infospace_config,
    load_infospace_config,
    save_infospace_config,
)
from markitect.infospace.entity_parser import parse_entity_directory
from markitect.infospace.state import build_state


def _load_config_or_exit(config_path: Optional[str] = None) -> tuple:
    """Resolve and load infospace.yaml, or exit with an error."""
    if config_path:
        p = Path(config_path)
    else:
        p = find_infospace_config()
    if p is None:
        click.echo("Error: No infospace.yaml found. Run 'markitect infospace init' first.", err=True)
        raise SystemExit(1)
    cfg = load_infospace_config(p)
    return cfg, p


@click.group(name="infospace")
def infospace_commands():
    """Manage infospaces — create, inspect, evaluate."""
    pass


# ── init ─────────────────────────────────────────────────────────────


@infospace_commands.command()
@click.option("--topic", required=True, help="Topic name for the infospace.")
@click.option("--domain", default="", help="Knowledge domain.")
@click.option("--sources", default="", help="Path to source material directory.")
@click.option("--discipline", multiple=True, help="Discipline name (repeatable).")
@click.option("--output", "-o", default="infospace.yaml", help="Output config file path.")
def init(topic: str, domain: str, sources: str, discipline: tuple, output: str):
    """Initialise a new infospace configuration file."""
    out_path = Path(output)
    if out_path.exists():
        click.echo(f"Error: {out_path} already exists.", err=True)
        raise SystemExit(1)

    disciplines = [DisciplineBinding(name=d) for d in discipline]
    config = InfospaceConfig(
        topic=TopicConfig(name=topic, domain=domain, sources=sources),
        disciplines=disciplines,
    )
    save_infospace_config(config, out_path)
    click.echo(f"Created {out_path}")


# ── status ───────────────────────────────────────────────────────────


@infospace_commands.command()
@click.option("--config", "config_path", default=None, help="Path to infospace.yaml.")
def status(config_path: Optional[str]):
    """Show infospace status — entity count, domains, evaluation state."""
    cfg, cfg_path = _load_config_or_exit(config_path)
    root = cfg_path.parent

    # Parse entities
    entities_dir = root / cfg.entities_dir
    entities = []
    if entities_dir.is_dir():
        entities = parse_entity_directory(entities_dir)

    # Load latest snapshot if available
    snapshot = None
    history_path = root / cfg.metrics_dir / "history.yaml"
    if history_path.is_file():
        from markitect.infospace.evaluation_io import read_history
        history = read_history(history_path)
        if history:
            snapshot = history[-1]

    state = build_state(cfg, entities=entities, snapshot=snapshot)

    click.echo(f"Infospace: {state.topic_name}")
    if cfg.topic.domain:
        click.echo(f"Domain:    {cfg.topic.domain}")
    click.echo(f"Entities:  {state.entity_count}")
    if state.domains:
        click.echo(f"Domains:   {', '.join(state.domains)}")
    if cfg.disciplines:
        names = [d.name for d in cfg.disciplines]
        click.echo(f"Disciplines: {', '.join(names)}")
    if state.has_evaluations:
        click.echo(f"Last evaluated: {state.latest_snapshot.created_at.isoformat()}")
    else:
        click.echo("Evaluations: none")


# ── entities ─────────────────────────────────────────────────────────


@infospace_commands.command()
@click.option("--config", "config_path", default=None, help="Path to infospace.yaml.")
@click.option(
    "--sort-by", "sort_key",
    type=click.Choice(["slug", "domain", "words"]),
    default="slug",
    help="Sort entities by field.",
)
def entities(config_path: Optional[str], sort_key: str):
    """List entities with metadata summary."""
    cfg, cfg_path = _load_config_or_exit(config_path)
    root = cfg_path.parent
    entities_dir = root / cfg.entities_dir

    if not entities_dir.is_dir():
        click.echo("No entities directory found.")
        return

    entity_list = parse_entity_directory(entities_dir)
    if not entity_list:
        click.echo("No entities found.")
        return

    # Sort
    if sort_key == "domain":
        entity_list.sort(key=lambda e: (e.domain or "", e.slug))
    elif sort_key == "words":
        entity_list.sort(key=lambda e: e.total_word_count, reverse=True)
    else:
        entity_list.sort(key=lambda e: e.slug)

    # Format as table
    click.echo(f"{'Slug':<40} {'Domain':<20} {'Words':>6}")
    click.echo("-" * 68)
    for e in entity_list:
        click.echo(f"{e.slug:<40} {(e.domain or '-'):<20} {e.total_word_count:>6}")
    click.echo(f"\nTotal: {len(entity_list)} entities")


# ── evaluate ─────────────────────────────────────────────────────────


@infospace_commands.command()
@click.option("--config", "config_path", default=None, help="Path to infospace.yaml.")
@click.option("--provider", default="openrouter", help="LLM provider (openrouter, openai, etc.).")
@click.option("--model", default=None, help="LLM model name.")
@click.option("--entity", "entity_slug", default=None, help="Evaluate a single entity by slug.")
@click.option("--chapter", default=None, help="Evaluate entities from a specific chapter.")
def evaluate(config_path, provider, model, entity_slug, chapter):
    """Evaluate entities using LLM-based quality assessment."""
    cfg, cfg_path = _load_config_or_exit(config_path)
    root = cfg_path.parent

    entities_dir = root / cfg.entities_dir
    if not entities_dir.is_dir():
        click.echo("Error: No entities directory found.", err=True)
        raise SystemExit(1)

    entity_list = parse_entity_directory(entities_dir)
    if not entity_list:
        click.echo("No entities to evaluate.")
        return

    # Filter
    if entity_slug:
        entity_list = [e for e in entity_list if e.slug == entity_slug]
        if not entity_list:
            click.echo(f"Error: Entity '{entity_slug}' not found.", err=True)
            raise SystemExit(1)
    elif chapter:
        entity_list = [e for e in entity_list if chapter in e.source_chapter]
        if not entity_list:
            click.echo(f"No entities found for chapter '{chapter}'.")
            return

    # Create adapter
    from markitect.llm import create_adapter
    from markitect.prompts.execution.models import RunConfig
    adapter = create_adapter(provider, model=model)
    run_config = RunConfig(model_name=model or "default", temperature=0.3, max_tokens=2000)

    # Progress callback
    def on_progress(done, total, result):
        status = result.status.upper()
        click.echo(f"  [{done}/{total}] {result.key}: {status}")

    click.echo(f"Evaluating {len(entity_list)} entities via {provider}...")

    from markitect.infospace.evaluate import run_entity_evaluation
    output_dir = root / cfg.evaluations_dir
    summary = run_entity_evaluation(
        config=cfg,
        entities=entity_list,
        adapter=adapter,
        run_config=run_config,
        output_dir=output_dir,
        progress_callback=on_progress,
    )

    click.echo(f"\nDone: {summary.succeeded} succeeded, {summary.failed} failed, {summary.skipped} skipped")
    if summary.total_tokens > 0:
        click.echo(f"Tokens used: {summary.total_tokens}")


# ── viability ────────────────────────────────────────────────────────


@infospace_commands.command()
@click.option("--config", "config_path", default=None, help="Path to infospace.yaml.")
def viability(config_path: Optional[str]):
    """Show viability dashboard — threshold checks and pass/fail."""
    cfg, cfg_path = _load_config_or_exit(config_path)

    if not cfg.viability:
        click.echo("No viability thresholds configured in infospace.yaml.")
        return

    # Try to load latest metrics
    root = cfg_path.parent
    metrics: dict = {}
    metrics_file = root / cfg.metrics_dir / "metrics.yaml"
    if metrics_file.is_file():
        import yaml
        raw = yaml.safe_load(metrics_file.read_text(encoding="utf-8"))
        if isinstance(raw, dict):
            metrics = {k: float(v) for k, v in raw.items() if isinstance(v, (int, float))}

    state = build_state(cfg, metrics=metrics if metrics else None)

    if not state.viability_results:
        click.echo("No metrics available. Run evaluations first.")
        click.echo("\nConfigured thresholds:")
        for name, t in cfg.viability.items():
            bounds = []
            if t.min is not None:
                bounds.append(f"min={t.min}")
            if t.max is not None:
                bounds.append(f"max={t.max}")
            click.echo(f"  {name}: {', '.join(bounds)}")
        return

    click.echo(f"{'Metric':<30} {'Value':>8} {'Threshold':>15} {'Status':>8}")
    click.echo("-" * 63)
    for r in state.viability_results:
        bounds = []
        if r.threshold.min is not None:
            bounds.append(f"min={r.threshold.min}")
        if r.threshold.max is not None:
            bounds.append(f"max={r.threshold.max}")
        status_str = "PASS" if r.passed else "FAIL"
        click.echo(
            f"{r.metric:<30} {r.value:>8.4f} {', '.join(bounds):>15} {status_str:>8}"
        )

    click.echo()
    if state.is_viable:
        click.echo(f"Viable: YES ({state.viability_pass_count}/{state.viability_total_count} thresholds met)")
    else:
        click.echo(f"Viable: NO ({state.viability_pass_count}/{state.viability_total_count} thresholds met)")