# SPDX-License-Identifier: GPL-3.0-only
"""Provider interfaces plus the shared summary prompt and a tolerant JSON parser.

Keeping the prompt and parser here means every LLM provider produces the same Summary
shape regardless of whether it is OpenAI-compatible, Anthropic, or a local model.
"""
from __future__ import annotations

import json
import re
from typing import Protocol

from ..models import Summary, Transcript

SUMMARY_SYSTEM = (
    "You are a meeting-notes assistant. Given a transcript, produce a concise overview, "
    "the key points, and any action items. Respond with ONLY a JSON object of the form "
    '{"overview": string, "key_points": [string], "action_items": [string]} and nothing '
    "else."
)


def summary_user_prompt(transcript_text: str) -> str:
    return f"Transcript:\n\n{transcript_text}\n\nProduce the JSON summary now."


def parse_summary(recording_id: str, model: str, raw: str) -> Summary:
    """Parse an LLM reply into a Summary, tolerating prose or code-fences around the JSON."""
    data: dict = {}
    match = re.search(r"\{.*\}", raw, re.DOTALL)
    if match:
        try:
            data = json.loads(match.group(0))
        except json.JSONDecodeError:
            data = {}
    return Summary(
        recording_id=recording_id,
        model=model,
        overview=str(data.get("overview") or raw.strip()[:1000]),
        key_points=[str(x) for x in (data.get("key_points") or [])],
        action_items=[str(x) for x in (data.get("action_items") or [])],
    )


class Transcriber(Protocol):
    name: str

    def transcribe(self, audio_path: str, language: str | None = None) -> Transcript: ...


class Summariser(Protocol):
    name: str

    def summarise(self, recording_id: str, transcript_text: str) -> Summary: ...