# === Standard Library ===
import os
import re
import json
import base64
import mimetypes
from pathlib import Path

# === Third-Party ===
import pandas as pd
import matplotlib.pyplot as plt
from PIL import Image
from dotenv import load_dotenv
from openai import OpenAI
from anthropic import Anthropic
from html import escape

# === Env & Clients ===
load_dotenv()
# Strip whitespace/newlines from API keys (common issue with env vars)
openai_api_key = os.getenv("OPENAI_API_KEY", "").strip()
anthropic_api_key = os.getenv("ANTHROPIC_API_KEY", "").strip()

# Both clients read keys from env by default; explicit is also fine:
openai_client = OpenAI(api_key=openai_api_key) if openai_api_key else OpenAI()
anthropic_client = Anthropic(api_key=anthropic_api_key) if anthropic_api_key else Anthropic()


def get_response(model: str, prompt: str) -> str:
    """Get response from LLM (OpenAI or Anthropic)."""
    if "claude" in model.lower() or "anthropic" in model.lower():
        # Check if Anthropic API key is available
        if not anthropic_api_key:
            raise ValueError("ANTHROPIC_API_KEY not set. Please add it as a secret in HuggingFace Spaces settings.")
        # Anthropic Claude format
        message = anthropic_client.messages.create(
            model=model,
            max_tokens=1000,
            messages=[{"role": "user", "content": [{"type": "text", "text": prompt}]}],
        )
        return message.content[0].text
    else:
        # Check if OpenAI API key is available
        if not openai_api_key:
            raise ValueError("OPENAI_API_KEY not set. Please add it as a secret in HuggingFace Spaces settings.")
        # Default to OpenAI format for all other models (gpt-4, o3-mini, o1, etc.)
        response = openai_client.responses.create(
            model=model,
            input=prompt,
        )
        return response.output_text


# === Data Loading ===
def load_and_prepare_data(csv_path: str) -> pd.DataFrame:
    """Load CSV and derive date parts commonly used in charts."""
    df = pd.read_csv(csv_path)
    # Be tolerant if 'date' exists
    if "date" in df.columns:
        df["date"] = pd.to_datetime(df["date"], errors="coerce")
        df["quarter"] = df["date"].dt.quarter
        df["month"] = df["date"].dt.month
        df["year"] = df["date"].dt.year
    return df


# === Helpers ===
def make_schema_text(df: pd.DataFrame) -> str:
    """Return a human-readable schema from a DataFrame."""
    return "\n".join(f"- {c}: {dt}" for c, dt in df.dtypes.items())


def ensure_execute_python_tags(text: str) -> str:
    """Normalize code to be wrapped in <execute_python>...</execute_python>."""
    text = text.strip()
    # Strip ```python fences if present
    text = re.sub(r"^```(?:python)?\s*|\s*```$", "", text).strip()
    if "<execute_python>" not in text:
        text = f"<execute_python>\n{text}\n</execute_python>"
    return text


def encode_image_b64(path: str) -> tuple[str, str]:
    """Return (media_type, base64_str) for an image file path."""
    mime, _ = mimetypes.guess_type(path)
    media_type = mime or "image/png"
    with open(path, "rb") as f:
        b64 = base64.b64encode(f.read()).decode("utf-8")
    return media_type, b64


def image_anthropic_call(model_name: str, prompt: str, media_type: str, b64: str) -> str:
    """
    Call Anthropic Claude (messages.create) with text+image and return *all* text blocks concatenated.
    Adds a system message to enforce strict JSON output.
    """
    if not anthropic_api_key:
        raise ValueError("ANTHROPIC_API_KEY not set. Please add it as a secret in HuggingFace Spaces settings.")
    msg = anthropic_client.messages.create(
        model=model_name,
        max_tokens=2000,
        temperature=0,
        system=(
            "You are a careful assistant. Respond with a single valid JSON object only. "
            "Do not include markdown, code fences, or commentary outside JSON."
        ),
        messages=[{
            "role": "user",
            "content": [
                {"type": "text", "text": prompt},
                {"type": "image", "source": {"type": "base64", "media_type": media_type, "data": b64}},
            ],
        }],
    )

    # Anthropic returns a list of content blocks; collect all text
    parts = []
    for block in (msg.content or []):
        if getattr(block, "type", None) == "text":
            parts.append(block.text)
    return "".join(parts).strip()


def image_openai_call(model_name: str, prompt: str, media_type: str, b64: str) -> str:
    """Call OpenAI with text+image input."""
    if not openai_api_key:
        raise ValueError("OPENAI_API_KEY not set. Please add it as a secret in HuggingFace Spaces settings.")
    data_url = f"data:{media_type};base64,{b64}"
    resp = openai_client.responses.create(
        model=model_name,
        input=[
            {
                "role": "user",
                "content": [
                    {"type": "input_text", "text": prompt},
                    {"type": "input_image", "image_url": data_url},
                ],
            }
        ],
    )
    content = (resp.output_text or "").strip()
    return content