import os
import gradio as gr
import requests
import inspect
import pandas as pd
from smolagents import tool, Tool, CodeAgent, DuckDuckGoSearchTool, HfApiModel, VisitWebpageTool, SpeechToTextTool, FinalAnswerTool
from dotenv import load_dotenv
import heapq
from collections import Counter
import re
from io import BytesIO
from youtube_transcript_api import YouTubeTranscriptApi
from langchain_community.tools.tavily_search import TavilySearchResults
from langchain_community.document_loaders import WikipediaLoader
from langchain_community.utilities import WikipediaAPIWrapper
from langchain_community.document_loaders import ArxivLoader

# (Keep Constants as is)
# --- Constants ---
DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"

#Load environment variables
load_dotenv()




from smolagents import Tool
from langchain_community.document_loaders import WikipediaLoader

class WikiSearchTool(Tool):
    name = "wiki_search"
    description = "Search Wikipedia for a query and return up to 2 results."
    inputs = {
        "query": {"type": "string", "description": "The search term for Wikipedia."}
    }
    output_type = "string"

    def forward(self, query: str) -> str:
        search_docs = WikipediaLoader(query=query, load_max_docs=2).load()

        formatted_search_docs = "\n\n---\n\n".join(
            [
                f'<Document source="{doc.metadata.get("source", "Wikipedia")}" page="{doc.metadata.get("page", "")}"/>\n{doc.page_content}\n</Document>'
                for doc in search_docs
            ]
        )
        return formatted_search_docs

    


class StringReverseTool(Tool):
    name = "reverse_message"
    description = "When you received a strange text, try to reverse it and perform action described in reversed message."
    inputs = {
        "message": {
            "type": "string",
            "description": "A message, which looks like strange and can be reversed to get actions to execute."
        }
    }
    output_type = "string"

    def __init__(self):
        return

    def forward(self, message: str):
        return message[::-1]

class KeywordsExtractorTool(Tool):
    """Extracts top 5 keywords from a given text based on frequency."""

    name = "keywords_extractor"
    description = "This tool returns the 5 most frequent keywords occur in provided block of text."

    inputs = {
        "text": {
            "type": "string",
            "description": "Text to analyze for keywords.",
        }
    }
    output_type = "string"

    def forward(self, text: str) -> str:
        try:
            all_words = re.findall(r'\b\w+\b', text.lower())
            conjunctions = {'a', 'and', 'of', 'is', 'in', 'to', 'the'}
            filtered_words = []
            for w in all_words:
                if w not in conjunctions:
                    filtered_words.push(w)
            word_counts = Counter(filtered_words)
            k = 5
            return heapq.nlargest(k, word_counts.items(), key=lambda x: x[1])
        except Exception as e:
            return f"Error during extracting most common words: {e}"

@tool
def parse_excel_to_json(task_id: str) -> dict:
    """
    For a given task_id fetch and parse an Excel file and save parsed data in structured JSON file.
    Args:
        task_id: An task ID to fetch.
        
    Returns:
        {
            "task_id": str,
            "sheets": {
                "SheetName1": [ {col1: val1, col2: val2, ...}, ... ],
                ...
            },
            "status": "Success" | "Error"
        }
    """
    url = f"https://agents-course-unit4-scoring.hf.space/files/{task_id}"

    try:
        response = requests.get(url, timeout=100)
        if response.status_code != 200:
            return {"task_id": task_id, "sheets": {}, "status": f"{response.status_code} - Failed"}

        xls_content = pd.ExcelFile(BytesIO(response.content))
        json_sheets = {}

        for sheet in xls_content.sheet_names:
            df = xls_content.parse(sheet)
            df = df.dropna(how="all")  
            rows = df.head(20).to_dict(orient="records")
            json_sheets[sheet] = rows

        return {
            "task_id": task_id,
            "sheets": json_sheets,
            "status": "Success"
        }

    except Exception as e:
        return {
            "task_id": task_id,
            "sheets": {},
            "status": f"Error in parsing Excel file: {str(e)}"
        }



class VideoTranscriptionTool(Tool):
    """Fetch transcripts from YouTube videos"""
    name = "transcript_video"
    description = "Fetch text transcript from YouTube movies with optional timestamps"
    inputs = {
        "url": {"type": "string", "description": "YouTube video URL or ID"},
        "include_timestamps": {"type": "boolean", "description": "If timestamps should be included in output", "nullable": True}
    }
    output_type = "string"

    def forward(self, url: str, include_timestamps: bool = False) -> str:

        if "youtube.com/watch" in url:
            video_id = url.split("v=")[1].split("&")[0]
        elif "youtu.be/" in url:
            video_id = url.split("youtu.be/")[1].split("?")[0]
        elif len(url.strip()) == 11:  # Direct ID
            video_id = url.strip()
        else:
            return f"YouTube URL or ID: {url} is invalid!"

        try:
            transcription = YouTubeTranscriptApi.get_transcript(video_id)

            if include_timestamps:
                formatted_transcription = []
                for part in transcription:
                    timestamp = f"{int(part['start']//60)}:{int(part['start']%60):02d}"
                    formatted_transcription.append(f"[{timestamp}] {part['text']}")
                return "\n".join(formatted_transcription)
            else:
                return " ".join([part['text'] for part in transcription])

        except Exception as e:
            return f"Error in extracting YouTube transcript: {str(e)}"

class BasicAgent:
    def __init__(self):
        token = os.environ.get("HF_API_TOKEN")
        model = HfApiModel(
            temperature=0.1,
            token=token
        )

        search_tool = DuckDuckGoSearchTool()
        wiki_search_tool = WikiSearchTool()
        str_reverse_tool = StringReverseTool()
        keywords_extract_tool = KeywordsExtractorTool()
        speech_to_text_tool = SpeechToTextTool()
        visit_webpage_tool = VisitWebpageTool()
        final_answer_tool = FinalAnswerTool()
        video_transcription_tool = VideoTranscriptionTool()

        system_prompt = f"""
You are an expert assistant who can solve any task using code blobs. You will be given a task to solve as best you can.
To do so, you have been given access to a list of tools: these tools are basically Python functions which you can call with code.
To solve the task, you must plan forward to proceed in a series of steps, in a cycle of 'Thought:', 'Code:', and 'Observation:' sequences.

At each step, in the 'Thought:' sequence, you should first explain your reasoning towards solving the task and the tools that you want to use.
Then in the 'Code:' sequence, you should write the code in simple Python. The code sequence must end with '<end_code>' sequence.
During each intermediate step, you can use 'print()' to save whatever important information you will then need.
These print outputs will then appear in the 'Observation:' field, which will be available as input for the next step.
In the end you have to return a final answer using the `final_answer` tool.

Here are a few examples using notional tools:
---
Task: "Generate an image of the oldest person in this document."

Thought: I will proceed step by step and use the following tools: `document_qa` to find the oldest person in the document, then `image_generator` to generate an image according to the answer.
Code:
```py
answer = document_qa(document=document, question="Who is the oldest person mentioned?")
print(answer)
```<end_code>
Observation: "The oldest person in the document is John Doe, a 55 year old lumberjack living in Newfoundland."

Thought: I will now generate an image showcasing the oldest person.
Code:
```py
image = image_generator("A portrait of John Doe, a 55-year-old man living in Canada.")
final_answer(image)
```<end_code>

---
Task: "What is the result of the following operation: 5 + 3 + 1294.678?"

Thought: I will use python code to compute the result of the operation and then return the final answer using the `final_answer` tool
Code:
```py
result = 5 + 3 + 1294.678
final_answer(result)
```<end_code>

---
Task:
"Answer the question in the variable `question` about the image stored in the variable `image`. The question is in French.
You have been provided with these additional arguments, that you can access using the keys as variables in your python code:
{'question': 'Quel est l'animal sur l'image?', 'image': 'path/to/image.jpg'}"

Thought: I will use the following tools: `translator` to translate the question into English and then `image_qa` to answer the question on the input image.
Code:
```py
translated_question = translator(question=question, src_lang="French", tgt_lang="English")
print(f"The translated question is {translated_question}.")
answer = image_qa(image=image, question=translated_question)
final_answer(f"The answer is {answer}")
```<end_code>

---
Task:
In a 1979 interview, Stanislaus Ulam discusses with Martin Sherwin about other great physicists of his time, including Oppenheimer.
What does he say was the consequence of Einstein learning too much math on his creativity, in one word?

Thought: I need to find and read the 1979 interview of Stanislaus Ulam with Martin Sherwin.
Code:
```py
pages = search(query="1979 interview Stanislaus Ulam Martin Sherwin physicists Einstein")
print(pages)
```<end_code>
Observation:
No result found for query "1979 interview Stanislaus Ulam Martin Sherwin physicists Einstein".

Thought: The query was maybe too restrictive and did not find any results. Let's try again with a broader query.
Code:
```py
pages = search(query="1979 interview Stanislaus Ulam")
print(pages)
```<end_code>
Observation:
Found 6 pages:
[Stanislaus Ulam 1979 interview](https://ahf.nuclearmuseum.org/voices/oral-histories/stanislaus-ulams-interview-1979/)

[Ulam discusses Manhattan Project](https://ahf.nuclearmuseum.org/manhattan-project/ulam-manhattan-project/)

(truncated)

Thought: I will read the first 2 pages to know more.
Code:
```py
for url in ["https://ahf.nuclearmuseum.org/voices/oral-histories/stanislaus-ulams-interview-1979/", "https://ahf.nuclearmuseum.org/manhattan-project/ulam-manhattan-project/"]:
    whole_page = visit_webpage(url)
    print(whole_page)
    print("\n" + "="*80 + "\n")  # Print separator between pages
```<end_code>
Observation:
Manhattan Project Locations:
Los Alamos, NM
Stanislaus Ulam was a Polish-American mathematician. He worked on the Manhattan Project at Los Alamos and later helped design the hydrogen bomb. In this interview, he discusses his work at
(truncated)

Thought: I now have the final answer: from the webpages visited, Stanislaus Ulam says of Einstein: "He learned too much mathematics and sort of diminished, it seems to me personally, it seems to me his purely physics creativity." Let's answer in one word.
Code:
```py
final_answer("diminished")
```<end_code>

---
Task: "Which city has the highest population: Guangzhou or Shanghai?"

Thought: I need to get the populations for both cities and compare them: I will use the tool `search` to get the population of both cities.
Code:
```py
for city in ["Guangzhou", "Shanghai"]:
    print(f"Population {city}:", search(f"{city} population")
```<end_code>
Observation:
Population Guangzhou: ['Guangzhou has a population of 15 million inhabitants as of 2021.']
Population Shanghai: '26 million (2019)'

Thought: Now I know that Shanghai has the highest population.
Code:
```py
final_answer("Shanghai")
```<end_code>

---
Task: "What is the current age of the pope, raised to the power 0.36?"

Thought: I will use the tool `wiki` to get the age of the pope, and confirm that with a web search.
Code:
```py
pope_age_wiki = wiki(query="current pope age")
print("Pope age as per wikipedia:", pope_age_wiki)
pope_age_search = web_search(query="current pope age")
print("Pope age as per google search:", pope_age_search)
```<end_code>
Observation:
Pope age: "The pope Francis is currently 88 years old."

Thought: I know that the pope is 88 years old. Let's compute the result using python code.
Code:
```py
pope_current_age = 88 ** 0.36
final_answer(pope_current_age)
```<end_code>

Above example were using notional tools that might not exist for you. 

Here are the rules you should always follow to solve your task:
1. Always provide a 'Thought:' sequence, and a 'Code:\n```py' sequence ending with '```<end_code>' sequence, else you will fail.
2. Use only variables that you have defined!
3. Always use the right arguments for the tools. DO NOT pass the arguments as a dict as in 'answer = wiki({'query': "What is the place where James Bond lives?"})', but use the arguments directly as in 'answer = wiki(query="What is the place where James Bond lives?")'.
4. Take care to not chain too many sequential tool calls in the same code block, especially when the output format is unpredictable. For instance, a call to search has an unpredictable return format, so do not have another tool call that depends on its output in the same block: rather output results with print() to use them in the next block.
5. Call a tool only when needed, and never re-do a tool call that you previously did with the exact same parameters.
6. Don't name any new variable with the same name as a tool: for instance don't name a variable 'final_answer'.
7. Never create any notional variables in our code, as having these in your logs will derail you from the true variables.
8. You can use imports in your code, but only from the following list of modules: {{authorized_imports}}
9. The state persists between code executions: so if in one step you've created variables or imported modules, these will all persist.
10. Don't give up! You're in charge of solving the task, not providing directions to solve it.
11. Return your final answer in a single line, formatted as follows: "FINAL ANSWER: [YOUR FINAL ANSWER]".
[YOUR FINAL ANSWER] should be a number, a string, or a comma-separated list of numbers and/or strings, depending on the question.

Now Begin! If you solve the task correctly, you will receive a reward of $1,000,000.
"""
        self.agent = CodeAgent(
            model=model,
            tools=[search_tool, wiki_search_tool, str_reverse_tool, keywords_extract_tool, speech_to_text_tool, visit_webpage_tool, final_answer_tool, parse_excel_to_json, video_transcription_tool],
            add_base_tools=True
        )
        self.agent.prompt_templates["system_prompt"] = self.agent.prompt_templates["system_prompt"] + system_prompt

    def __call__(self, question: str) -> str:
        print(f"Agent received question (first 50 chars): {question[:50]}...")
        answer = self.agent.run(question)
        print(f"Agent returning answer: {answer}")
        return answer

def run_and_submit_all( profile: gr.OAuthProfile | None):
    """
    Fetches all questions, runs the BasicAgent on them, submits all answers,
    and displays the results.
    """
    # --- Determine HF Space Runtime URL and Repo URL ---
    space_id = os.getenv("SPACE_ID") # Get the SPACE_ID for sending link to the code

    if profile:
        username= f"{profile.username}"
        print(f"User logged in: {username}")
    else:
        print("User not logged in.")
        return "Please Login to Hugging Face with the button.", None

    api_url = DEFAULT_API_URL
    questions_url = f"{api_url}/questions"
    submit_url = f"{api_url}/submit"

    # 1. Instantiate Agent ( modify this part to create your agent)
    try:
        agent = BasicAgent()
    except Exception as e:
        print(f"Error instantiating agent: {e}")
        return f"Error initializing agent: {e}", None
    # In the case of an app running as a hugging Face space, this link points toward your codebase ( usefull for others so please keep it public)
    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
    print(agent_code)

    # 2. Fetch Questions
    print(f"Fetching questions from: {questions_url}")
    try:
        response = requests.get(questions_url, timeout=15)
        response.raise_for_status()
        questions_data = response.json()
        if not questions_data:
             print("Fetched questions list is empty.")
             return "Fetched questions list is empty or invalid format.", None
        print(f"Fetched {len(questions_data)} questions.")
    except requests.exceptions.RequestException as e:
        print(f"Error fetching questions: {e}")
        return f"Error fetching questions: {e}", None
    except requests.exceptions.JSONDecodeError as e:
         print(f"Error decoding JSON response from questions endpoint: {e}")
         print(f"Response text: {response.text[:500]}")
         return f"Error decoding server response for questions: {e}", None
    except Exception as e:
        print(f"An unexpected error occurred fetching questions: {e}")
        return f"An unexpected error occurred fetching questions: {e}", None

    # 3. Run your Agent
    results_log = []
    answers_payload = []
    print(f"Running agent on {len(questions_data)} questions...")
    for item in questions_data:
        task_id = item.get("task_id")
        question_text = item.get("question")
        if not task_id or question_text is None:
            print(f"Skipping item with missing task_id or question: {item}")
            continue
        try:
            submitted_answer = agent(question_text)
            answers_payload.append({"task_id": task_id, "submitted_answer": submitted_answer})
            results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": submitted_answer})
        except Exception as e:
             print(f"Error running agent on task {task_id}: {e}")
             results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": f"AGENT ERROR: {e}"})

    if not answers_payload:
        print("Agent did not produce any answers to submit.")
        return "Agent did not produce any answers to submit.", pd.DataFrame(results_log)

    # 4. Prepare Submission 
    submission_data = {"username": username.strip(), "agent_code": agent_code, "answers": answers_payload}
    status_update = f"Agent finished. Submitting {len(answers_payload)} answers for user '{username}'..."
    print(status_update)

    # 5. Submit
    print(f"Submitting {len(answers_payload)} answers to: {submit_url}")
    try:
        response = requests.post(submit_url, json=submission_data, timeout=60)
        response.raise_for_status()
        result_data = response.json()
        final_status = (
            f"Submission Successful!\n"
            f"User: {result_data.get('username')}\n"
            f"Overall Score: {result_data.get('score', 'N/A')}% "
            f"({result_data.get('correct_count', '?')}/{result_data.get('total_attempted', '?')} correct)\n"
            f"Message: {result_data.get('message', 'No message received.')}"
        )
        print("Submission successful.")
        results_df = pd.DataFrame(results_log)
        return final_status, results_df
    except requests.exceptions.HTTPError as e:
        error_detail = f"Server responded with status {e.response.status_code}."
        try:
            error_json = e.response.json()
            error_detail += f" Detail: {error_json.get('detail', e.response.text)}"
        except requests.exceptions.JSONDecodeError:
            error_detail += f" Response: {e.response.text[:500]}"
        status_message = f"Submission Failed: {error_detail}"
        print(status_message)
        results_df = pd.DataFrame(results_log)
        return status_message, results_df
    except requests.exceptions.Timeout:
        status_message = "Submission Failed: The request timed out."
        print(status_message)
        results_df = pd.DataFrame(results_log)
        return status_message, results_df
    except requests.exceptions.RequestException as e:
        status_message = f"Submission Failed: Network error - {e}"
        print(status_message)
        results_df = pd.DataFrame(results_log)
        return status_message, results_df
    except Exception as e:
        status_message = f"An unexpected error occurred during submission: {e}"
        print(status_message)
        results_df = pd.DataFrame(results_log)
        return status_message, results_df


# --- Build Gradio Interface using Blocks ---
with gr.Blocks() as demo:
    gr.Markdown("# Basic Agent Evaluation Runner")
    gr.Markdown(
        """
        **Instructions:**
        1.  Please clone this space, then modify the code to define your agent's logic, the tools, the necessary packages, etc ...
        2.  Log in to your Hugging Face account using the button below. This uses your HF username for submission.
        3.  Click 'Run Evaluation & Submit All Answers' to fetch questions, run your agent, submit answers, and see the score.
        ---
        **Disclaimers:**
        Once clicking on the "submit button, it can take quite some time ( this is the time for the agent to go through all the questions).
        This space provides a basic setup and is intentionally sub-optimal to encourage you to develop your own, more robust solution. For instance for the delay process of the submit button, a solution could be to cache the answers and submit in a seperate action or even to answer the questions in async.
        """
    )

    gr.LoginButton()

    run_button = gr.Button("Run Evaluation & Submit All Answers")

    status_output = gr.Textbox(label="Run Status / Submission Result", lines=5, interactive=False)
    # Removed max_rows=10 from DataFrame constructor
    results_table = gr.DataFrame(label="Questions and Agent Answers", wrap=True)

    run_button.click(
        fn=run_and_submit_all,
        outputs=[status_output, results_table]
    )

if __name__ == "__main__":
    print("\n" + "-"*30 + " App Starting " + "-"*30)
    # Check for SPACE_HOST and SPACE_ID at startup for information
    space_host_startup = os.getenv("SPACE_HOST")
    space_id_startup = os.getenv("SPACE_ID") # Get SPACE_ID at startup

    if space_host_startup:
        print(f"✅ SPACE_HOST found: {space_host_startup}")
        print(f"   Runtime URL should be: https://{space_host_startup}.hf.space")
    else:
        print("ℹ️  SPACE_HOST environment variable not found (running locally?).")

    if space_id_startup: # Print repo URLs if SPACE_ID is found
        print(f"✅ SPACE_ID found: {space_id_startup}")
        print(f"   Repo URL: https://huggingface.co/spaces/{space_id_startup}")
        print(f"   Repo Tree URL: https://huggingface.co/spaces/{space_id_startup}/tree/main")
    else:
        print("ℹ️  SPACE_ID environment variable not found (running locally?). Repo URL cannot be determined.")

    print("-"*(60 + len(" App Starting ")) + "\n")

    print("Launching Gradio Interface for Basic Agent Evaluation...")
    demo.launch(debug=True, share=False)