"""Checkpoint writer/reader for pipeline state persistence.

Each stage writes a checkpoint after completion. The orchestrator uses
checkpoints to resume pipelines and to present state at human checkpoints.
"""

from __future__ import annotations

import json
from functools import lru_cache
from datetime import datetime, timezone
from pathlib import Path
from typing import Any, Optional

import jsonschema

from schemas.artifacts import ARTIFACT_NAMES, validate_artifact

STAGES = ["research", "proposal", "idea", "script", "scene_plan", "assets", "edit", "compose", "publish"]

CANONICAL_STAGE_ARTIFACTS = {
    "research": "research_brief",
    "proposal": "proposal_packet",
    "idea": "brief",
    "script": "script",
    "scene_plan": "scene_plan",
    "assets": "asset_manifest",
    "edit": "edit_decisions",
    "compose": "render_report",
    "publish": "publish_log",
}

CHECKPOINT_SCHEMA_PATH = (
    Path(__file__).resolve().parent.parent
    / "schemas"
    / "checkpoints"
    / "checkpoint.schema.json"
)


class CheckpointValidationError(ValueError):
    """Raised when a checkpoint or its canonical artifacts are invalid."""


@lru_cache(maxsize=1)
def _load_checkpoint_schema() -> dict[str, Any]:
    with open(CHECKPOINT_SCHEMA_PATH) as f:
        return json.load(f)


def _validate_artifacts_for_stage(
    stage: str,
    status: str,
    artifacts: dict[str, Any],
) -> None:
    required_artifact = CANONICAL_STAGE_ARTIFACTS[stage]
    if status in {"completed", "awaiting_human"} and required_artifact not in artifacts:
        raise CheckpointValidationError(
            f"Stage {stage!r} with status {status!r} must include "
            f"canonical artifact {required_artifact!r}"
        )

    for artifact_name, artifact_data in artifacts.items():
        if artifact_name not in ARTIFACT_NAMES:
            continue
        if not isinstance(artifact_data, dict):
            raise CheckpointValidationError(
                f"Artifact {artifact_name!r} must be a JSON object matching its schema"
            )
        try:
            validate_artifact(artifact_name, artifact_data)
        except Exception as exc:
            raise CheckpointValidationError(
                f"Artifact {artifact_name!r} failed schema validation: {exc}"
            ) from exc


def validate_checkpoint(checkpoint: dict[str, Any]) -> None:
    """Validate checkpoint structure and canonical artifact payloads."""
    stage = checkpoint.get("stage")
    status = checkpoint.get("status")
    artifacts = checkpoint.get("artifacts")

    if not isinstance(stage, str) or stage not in STAGES:
        raise CheckpointValidationError(f"Invalid stage: {stage!r}")
    if not isinstance(status, str):
        raise CheckpointValidationError(f"Invalid status: {status!r}")
    if not isinstance(artifacts, dict):
        raise CheckpointValidationError("Checkpoint artifacts must be a dictionary")

    _validate_artifacts_for_stage(stage, status, artifacts)

    try:
        jsonschema.validate(instance=checkpoint, schema=_load_checkpoint_schema())
    except jsonschema.ValidationError as exc:
        raise CheckpointValidationError(f"Checkpoint failed schema validation: {exc.message}") from exc


def _checkpoint_path(pipeline_dir: Path, project_id: str, stage: str) -> Path:
    return pipeline_dir / project_id / f"checkpoint_{stage}.json"


def write_checkpoint(
    pipeline_dir: Path,
    project_id: str,
    stage: str,
    status: str,
    artifacts: dict[str, Any],
    *,
    pipeline_type: Optional[str] = None,
    style_playbook: Optional[str] = None,
    checkpoint_policy: str = "guided",
    human_approval_required: bool = False,
    human_approved: bool = False,
    review: Optional[dict] = None,
    cost_snapshot: Optional[dict] = None,
    error: Optional[str] = None,
    metadata: Optional[dict] = None,
) -> Path:
    """Write a checkpoint file for a pipeline stage."""
    if stage not in STAGES:
        raise ValueError(f"Invalid stage: {stage!r}. Must be one of {STAGES}")

    checkpoint = {
        "version": "1.0",
        "project_id": project_id,
        "stage": stage,
        "status": status,
        "timestamp": datetime.now(timezone.utc).isoformat(),
        "checkpoint_policy": checkpoint_policy,
        "human_approval_required": human_approval_required,
        "human_approved": human_approved,
        "artifacts": artifacts,
    }

    if pipeline_type is not None:
        checkpoint["pipeline_type"] = pipeline_type
    if style_playbook is not None:
        checkpoint["style_playbook"] = style_playbook
    if review is not None:
        checkpoint["review"] = review
    if cost_snapshot is not None:
        checkpoint["cost_snapshot"] = cost_snapshot
    if error is not None:
        checkpoint["error"] = error
    if metadata is not None:
        checkpoint["metadata"] = metadata

    validate_checkpoint(checkpoint)

    path = _checkpoint_path(pipeline_dir, project_id, stage)
    path.parent.mkdir(parents=True, exist_ok=True)
    with open(path, "w") as f:
        json.dump(checkpoint, f, indent=2)

    return path


def read_checkpoint(
    pipeline_dir: Path, project_id: str, stage: str
) -> Optional[dict[str, Any]]:
    """Read a checkpoint file. Returns None if not found."""
    path = _checkpoint_path(pipeline_dir, project_id, stage)
    if not path.exists():
        return None
    with open(path) as f:
        checkpoint = json.load(f)
    validate_checkpoint(checkpoint)
    return checkpoint


def get_latest_checkpoint(
    pipeline_dir: Path, project_id: str
) -> Optional[dict[str, Any]]:
    """Find the most recent checkpoint for a project (by file mtime)."""
    project_dir = pipeline_dir / project_id
    if not project_dir.exists():
        return None

    checkpoints = sorted(
        project_dir.glob("checkpoint_*.json"),
        key=lambda p: p.stat().st_mtime,
        reverse=True,
    )
    if not checkpoints:
        return None

    with open(checkpoints[0]) as f:
        checkpoint = json.load(f)
    validate_checkpoint(checkpoint)
    return checkpoint


def get_completed_stages(pipeline_dir: Path, project_id: str) -> list[str]:
    """Return list of stages that have a completed checkpoint."""
    completed = []
    for stage in STAGES:
        cp = read_checkpoint(pipeline_dir, project_id, stage)
        if cp and cp.get("status") == "completed":
            completed.append(stage)
    return completed


def get_next_stage(pipeline_dir: Path, project_id: str) -> Optional[str]:
    """Determine the next stage to run based on completed checkpoints."""
    completed = set(get_completed_stages(pipeline_dir, project_id))
    for stage in STAGES:
        if stage not in completed:
            return stage
    return None