#!/usr/bin/env python3
"""LLM-backed Working Protocol V2 renderer with deterministic contract checks."""

from __future__ import annotations

import argparse
import json
import re
import sys
import time
from dataclasses import dataclass
from datetime import datetime
from pathlib import Path
from typing import Any

import requests

try:
    from meeting_lab.llm.prompts import load_prompt
except ModuleNotFoundError:  # pragma: no cover - used by repository-root tests.
    from src.meeting_lab.llm.prompts import load_prompt


DEFAULT_MODEL = "qwen3.5:9b"
DEFAULT_ENDPOINT = "http://127.0.0.1:11434/api/generate"
DEFAULT_NUM_CTX = 32768
DEFAULT_NUM_PREDICT = 4096
DEFAULT_TIMEOUT = 1800
PROMPT_NAME = "working_protocol.md"
REQUIRED_TITLE = "# Working Protocol"
ALLOWED_TOPIC_SECTIONS = {
    "Background",
    "Decisions",
    "Action Items",
    "Open Questions",
}
GENERIC_SUMMARY_HEADINGS = {
    "Entscheidungen",
    "Decisions",
    "Handlungsaufträge",
    "Handlungsauftraege",
    "Action Items",
    "Offene Fragen",
    "Open Questions",
    "Technische Details",
    "Technical Details",
    "Fakten",
    "Facts",
    "Zusammenfassung",
    "Summary",
    "Konsolidierter Projektstatusbericht",
}
HEADING_RE = re.compile(r"^(#{1,6})\s+(.+?)\s*$")


class WorkingProtocolValidationError(ValueError):
    """Raised when rendered Markdown violates the Working Protocol V2 contract."""


@dataclass(frozen=True)
class WorkingProtocolValidationReport:
    valid: bool
    violations: list[dict[str, Any]]

    def to_dict(self) -> dict[str, Any]:
        return {"valid": self.valid, "violations": self.violations}


def parse_args() -> argparse.Namespace:
    parser = argparse.ArgumentParser(
        description="Render a consolidated meeting representation as Working Protocol V2."
    )
    parser.add_argument("input", type=Path, help="Consolidated meeting JSON input.")
    parser.add_argument(
        "-o",
        "--output-dir",
        type=Path,
        required=True,
        help="Directory for working_protocol.md, raw response, validation and metadata.",
    )
    parser.add_argument(
        "--model",
        default=DEFAULT_MODEL,
        help=f"Ollama model name (default: {DEFAULT_MODEL}).",
    )
    parser.add_argument(
        "--endpoint",
        default=DEFAULT_ENDPOINT,
        help=f"Ollama generate endpoint (default: {DEFAULT_ENDPOINT}).",
    )
    parser.add_argument(
        "--timeout",
        type=int,
        default=DEFAULT_TIMEOUT,
        help=f"HTTP timeout in seconds (default: {DEFAULT_TIMEOUT}).",
    )
    parser.add_argument(
        "--num-ctx",
        type=int,
        default=DEFAULT_NUM_CTX,
        help=f"Context window tokens (default: {DEFAULT_NUM_CTX}).",
    )
    parser.add_argument(
        "--num-predict",
        type=int,
        default=DEFAULT_NUM_PREDICT,
        help=f"Maximum generated tokens (default: {DEFAULT_NUM_PREDICT}).",
    )
    thinking = parser.add_mutually_exclusive_group()
    thinking.add_argument("--think", dest="think", action="store_true")
    thinking.add_argument("--no-think", dest="think", action="store_false")
    parser.set_defaults(think=False)
    return parser.parse_args()


def build_renderer_prompt(input_text: str) -> str:
    return f"{load_prompt(PROMPT_NAME)}\n\nINPUT JSON:\n{input_text}\n"


def response_text_from_ollama_data(data: dict[str, Any]) -> str:
    text = data.get("response")
    if isinstance(text, str):
        return text
    message = data.get("message")
    if isinstance(message, dict) and isinstance(message.get("content"), str):
        return message["content"]
    return ""


def build_ollama_payload(
    model: str,
    prompt: str,
    num_ctx: int,
    num_predict: int,
    think: bool,
) -> dict[str, Any]:
    return {
        "model": model,
        "prompt": prompt,
        "think": think,
        "stream": False,
        "options": {
            "temperature": 0.0,
            "num_ctx": num_ctx,
            "num_predict": num_predict,
        },
    }


def call_ollama(
    endpoint: str,
    payload: dict[str, Any],
    timeout: int,
) -> tuple[dict[str, Any], float]:
    start = time.perf_counter()
    response = requests.post(endpoint, json=payload, timeout=timeout)
    runtime = time.perf_counter() - start
    response.raise_for_status()
    data = response.json()
    if not isinstance(data, dict):
        raise ValueError("Ollama response must be a JSON object.")
    return data, runtime


def normalize_heading_whitespace(line: str) -> str:
    match = HEADING_RE.match(line.strip())
    if not match:
        return line.rstrip()
    return f"{match.group(1)} {match.group(2).strip()}"


def clean_working_protocol_markdown(text: str) -> str:
    """
    Remove only non-semantic wrapper text before an existing protocol heading.

    The cleanup does not create headings or transform a categorized summary into
    a Working Protocol. It only makes an already present contract heading the
    first byte of the candidate document.
    """
    text = text.replace("\r\n", "\n").replace("\r", "\n")
    lines = text.split("\n")
    start_index: int | None = None
    for index, line in enumerate(lines):
        if normalize_heading_whitespace(line) == REQUIRED_TITLE:
            start_index = index
            break
    if start_index is None:
        return text.lstrip()

    cleaned_lines = lines[start_index:]
    if cleaned_lines:
        cleaned_lines[0] = REQUIRED_TITLE
    return "\n".join(normalize_heading_whitespace(line) for line in cleaned_lines).strip() + "\n"


def validate_markdown_shape(markdown: str) -> list[dict[str, Any]]:
    violations: list[dict[str, Any]] = []
    if markdown.count("```") % 2 != 0:
        violations.append(
            {
                "type": "malformed_markdown",
                "reason": "unclosed_fenced_code_block",
            }
        )

    seen_title = False
    seen_topic = False
    current_topic_has_section = False
    topic_count = 0
    section_count = 0

    for line_number, line in enumerate(markdown.splitlines(), start=1):
        match = HEADING_RE.match(line)
        if not match:
            continue
        level = len(match.group(1))
        title = match.group(2).strip().strip("*")

        if level == 1:
            if line_number != 1 or title != "Working Protocol":
                violations.append(
                    {
                        "type": "invalid_heading",
                        "line": line_number,
                        "heading": line,
                        "reason": "only the first line may be '# Working Protocol'",
                    }
                )
            seen_title = True
            continue

        if not seen_title:
            violations.append(
                {
                    "type": "invalid_heading_order",
                    "line": line_number,
                    "heading": line,
                    "reason": "heading appears before required title",
                }
            )
            continue

        if level == 2:
            topic_count += 1
            seen_topic = True
            current_topic_has_section = False
            if title in GENERIC_SUMMARY_HEADINGS:
                violations.append(
                    {
                        "type": "generic_summary_framing",
                        "line": line_number,
                        "heading": line,
                        "reason": "top-level category heading is not a topic",
                    }
                )
            continue

        if level == 3:
            if not seen_topic:
                violations.append(
                    {
                        "type": "missing_topic",
                        "line": line_number,
                        "heading": line,
                        "reason": "section appears before any topic heading",
                    }
                )
            if title not in ALLOWED_TOPIC_SECTIONS:
                violations.append(
                    {
                        "type": "unknown_topic_section",
                        "line": line_number,
                        "heading": line,
                        "allowed": sorted(ALLOWED_TOPIC_SECTIONS),
                    }
                )
            else:
                section_count += 1
                current_topic_has_section = True
            continue

        violations.append(
            {
                "type": "unsupported_heading_level",
                "line": line_number,
                "heading": line,
                "reason": "Working Protocol V2 uses h1 title, h2 topics and h3 sections only",
            }
        )

    if seen_topic and not current_topic_has_section:
        # This catches the last topic; earlier empty topics are caught below by
        # counting consecutive h2 headings.
        pass

    h2_without_section = _topic_headings_without_sections(markdown)
    violations.extend(h2_without_section)

    if topic_count == 0:
        violations.append(
            {
                "type": "missing_topic",
                "reason": "document must contain at least one '## Topic title' section",
            }
        )
    if section_count == 0:
        violations.append(
            {
                "type": "missing_topic_sections",
                "reason": "document must contain at least one allowed h3 topic section",
            }
        )
    return violations


def _topic_headings_without_sections(markdown: str) -> list[dict[str, Any]]:
    violations: list[dict[str, Any]] = []
    current_topic: tuple[int, str] | None = None
    current_has_section = False

    for line_number, line in enumerate(markdown.splitlines(), start=1):
        match = HEADING_RE.match(line)
        if not match:
            continue
        level = len(match.group(1))
        if level == 2:
            if current_topic is not None and not current_has_section:
                violations.append(
                    {
                        "type": "empty_topic",
                        "line": current_topic[0],
                        "heading": current_topic[1],
                        "reason": "topic has no allowed h3 section",
                    }
                )
            current_topic = (line_number, line)
            current_has_section = False
        elif level == 3 and current_topic is not None:
            title = match.group(2).strip().strip("*")
            if title in ALLOWED_TOPIC_SECTIONS:
                current_has_section = True

    if current_topic is not None and not current_has_section:
        violations.append(
            {
                "type": "empty_topic",
                "line": current_topic[0],
                "heading": current_topic[1],
                "reason": "topic has no allowed h3 section",
            }
        )
    return violations


def validate_working_protocol_markdown(markdown: str) -> WorkingProtocolValidationReport:
    violations: list[dict[str, Any]] = []
    if not markdown.startswith(REQUIRED_TITLE):
        violations.append(
            {
                "type": "missing_required_heading",
                "expected": REQUIRED_TITLE,
                "reason": "document must begin exactly with '# Working Protocol'",
            }
        )
    elif not markdown.startswith(REQUIRED_TITLE + "\n"):
        violations.append(
            {
                "type": "invalid_required_heading",
                "expected": REQUIRED_TITLE,
                "reason": "required heading must occupy the complete first line",
            }
        )

    if markdown.startswith(REQUIRED_TITLE):
        violations.extend(validate_markdown_shape(markdown))

    return WorkingProtocolValidationReport(
        valid=len(violations) == 0,
        violations=violations,
    )


def write_json(path: Path, data: Any) -> None:
    path.parent.mkdir(parents=True, exist_ok=True)
    path.write_text(json.dumps(data, ensure_ascii=False, indent=2) + "\n", encoding="utf-8")


def render_working_protocol(
    input_path: Path,
    output_dir: Path,
    model: str = DEFAULT_MODEL,
    endpoint: str = DEFAULT_ENDPOINT,
    timeout: int = DEFAULT_TIMEOUT,
    num_ctx: int = DEFAULT_NUM_CTX,
    num_predict: int = DEFAULT_NUM_PREDICT,
    think: bool = False,
) -> dict[str, Any]:
    output_dir.mkdir(parents=True, exist_ok=True)
    prompt_path = Path("prompts") / PROMPT_NAME
    raw_response_path = output_dir / "raw_model_response.json"
    raw_text_path = output_dir / "raw_model_response.txt"
    candidate_path = output_dir / "cleaned_candidate.md"
    validation_path = output_dir / "validation_report.json"
    protocol_path = output_dir / "working_protocol.md"
    metadata_path = output_dir / "metadata.json"
    report_path = output_dir / "report.md"

    input_text = input_path.read_text(encoding="utf-8-sig")
    prompt = build_renderer_prompt(input_text)
    payload = build_ollama_payload(model, prompt, num_ctx, num_predict, think)

    data, runtime = call_ollama(endpoint, payload, timeout)
    response_text = response_text_from_ollama_data(data)
    raw_response_path.write_text(
        json.dumps(data, ensure_ascii=False, indent=2) + "\n",
        encoding="utf-8",
    )
    raw_text_path.write_text(response_text, encoding="utf-8")

    cleaned = clean_working_protocol_markdown(response_text)
    candidate_path.write_text(cleaned, encoding="utf-8")
    validation = validate_working_protocol_markdown(cleaned)
    write_json(validation_path, validation.to_dict())

    if validation.valid:
        protocol_path.write_text(cleaned, encoding="utf-8")
    elif protocol_path.exists():
        protocol_path.unlink()

    metadata = {
        "model": model,
        "endpoint": endpoint,
        "think": think,
        "stream": False,
        "temperature": 0.0,
        "num_ctx": num_ctx,
        "num_predict": num_predict,
        "timeout_seconds": timeout,
        "request_count": 1,
        "runtime_seconds": runtime,
        "prompt_path": str(prompt_path.resolve()),
        "input_path": str(input_path.resolve()),
        "output_path": str(protocol_path.resolve()) if validation.valid else None,
        "raw_response_path": str(raw_response_path.resolve()),
        "raw_text_path": str(raw_text_path.resolve()),
        "cleaned_candidate_path": str(candidate_path.resolve()),
        "validation_report_path": str(validation_path.resolve()),
        "http_status_code": 200,
        "response_text_length": len(response_text),
        "candidate_text_length": len(cleaned),
        "valid": validation.valid,
        "readable_markdown": validation.valid,
        "top_level_json_keys": sorted(data.keys()),
        "done": data.get("done"),
        "done_reason": data.get("done_reason"),
        "total_duration": data.get("total_duration"),
        "load_duration": data.get("load_duration"),
        "prompt_eval_count": data.get("prompt_eval_count"),
        "prompt_eval_duration": data.get("prompt_eval_duration"),
        "eval_count": data.get("eval_count"),
        "eval_duration": data.get("eval_duration"),
        "created_at": datetime.now().isoformat(timespec="seconds"),
    }
    write_json(metadata_path, metadata)

    lines = [
        "# Working Protocol Renderer V2 Report",
        "",
        f"- Result: {'valid renderer run' if validation.valid else 'invalid renderer run'}",
        f"- Model: `{model}`",
        f"- Runtime: {runtime:.3f} seconds",
        f"- Request count: 1",
        f"- Valid: {validation.valid}",
        f"- Violations: {len(validation.violations)}",
        f"- Raw response path: `{raw_response_path}`",
        f"- Cleaned candidate path: `{candidate_path}`",
        f"- Validation report path: `{validation_path}`",
        f"- Output path: `{protocol_path if validation.valid else 'not written'}`",
    ]
    report_path.write_text("\n".join(lines) + "\n", encoding="utf-8")
    return metadata


def main() -> int:
    args = parse_args()
    try:
        metadata = render_working_protocol(
            input_path=args.input,
            output_dir=args.output_dir,
            model=args.model,
            endpoint=args.endpoint,
            timeout=args.timeout,
            num_ctx=args.num_ctx,
            num_predict=args.num_predict,
            think=args.think,
        )
    except requests.ConnectionError as exc:
        print(f"Error: Ollama is not reachable at {args.endpoint}: {exc}", file=sys.stderr)
        return 1
    except requests.Timeout as exc:
        print(f"Error: Ollama request timed out after {args.timeout} seconds: {exc}", file=sys.stderr)
        return 1
    except requests.HTTPError as exc:
        print(f"Error: Ollama returned an HTTP error: {exc}", file=sys.stderr)
        return 1
    except (OSError, UnicodeError, ValueError, json.JSONDecodeError) as exc:
        print(f"Error: {exc}", file=sys.stderr)
        return 1

    print(f"Runtime seconds:                 {metadata['runtime_seconds']:.3f}")
    print(f"Validation result:               {'passed' if metadata['valid'] else 'failed'}")
    print(f"Output:                          {metadata['output_path'] or 'not written'}")
    print(f"Raw model response:              {metadata['raw_response_path']}")
    print(f"Validation report:               {metadata['validation_report_path']}")
    return 0 if metadata["valid"] else 1


if __name__ == "__main__":
    raise SystemExit(main())