functions/writer_agent.py

'''Agent responsible for writing the resume based on user provided context'''

import ast
import json
import logging
import os
from openai import OpenAI
from configuration import (
    INFERENCE_URL,
    WRITER_INSTRUCTIONS,
    WRITER_MODEL,
    REPO_SELECTION_PROMPT,
    PROJECTS_SECTION_PROMPT
)


# pylint: disable=broad-exception-caught


def write_resume(linkedin_resume: dict, github_repositories: list, job_call: dict) -> str:

    """
    Generates a resume based on the provided content.

    Args:
        linkedin_resume (dict): Resume content extracted from linkedin profile.
        github_repositories (dict): Information about the applicants GitHub repositories.
        job_summary (dict): Extracted/summarized job call information.

    Returns:
        str: The generated resume.
    """

    logger = logging.getLogger(f'{__name__}.write_resume')

    logger.info("Selecting relevant GitHub repositories based on job call")
    project_repos = _choose_repositories(github_repositories, job_call)

    logger.info("Writing projects section of the resume")
    projects = _write_projects_section(project_repos, job_call)


# Let the model select the most relevant repositories based on the job call
    client = OpenAI(
        base_url=INFERENCE_URL,
        api_key=os.environ.get("API_KEY", "dummy-key-for-testing")
    )

    prompt = f'JOB CALL\n{job_call}\nLINKEDIN RESUME\n{linkedin_resume}\nPROJECTS\n{projects}'


    messages = [
        {
            'role': 'system',
            'content': WRITER_INSTRUCTIONS
        },
        {
            'role': 'user',
            'content': prompt
        }
    ]

    completion_args = {
        'model': WRITER_MODEL,
        'messages': messages,
    }

    try:
        response = client.chat.completions.create(**completion_args)

    except Exception as e:
        response = None
        logger.error('Error during job summarization API call: %s', e)

    if response is not None:
        response = response.choices[0].message.content

    # Create data directory if it doesn't exist
    data_dir = 'data'

    if not os.path.exists(data_dir):

        os.makedirs(data_dir)
        logger.info("Created data directory: %s", data_dir)

    # Save the resume to resume.md in the data directory
    resume_file_path = os.path.join(data_dir, 'resume.md')

    try:
        with open(resume_file_path, 'w', encoding='utf-8') as f:
            f.write(response)

        logger.info("Resume saved to: %s", resume_file_path)

    except Exception as e:
        logger.error("Failed to save resume to file: %s", e)

    return response


def _choose_repositories(github_repositories: list, job_call: dict) -> list:
    """
    Choose relevant GitHub repositories based on the job call requirements.

    Args:
        github_repositories (dict): Information about the applicants GitHub repositories.
        job_call (dict): Extracted/summarized job call information.

    Returns:
        list: Filtered list of relevant repositories.
    """

    logger = logging.getLogger(f'{__name__}._choose_repositories')

    # Create a new repo list without the full README text - this way we can save on input tokens
    # by only sending the model the repo metadata, title, description, topics, etc.
    repo_data = [
        {k: v for k, v in d.items() if k != 'readme'}
        for d in github_repositories
    ]

    # Let the model select the most relevant repositories based on the job call
    client = OpenAI(
        base_url=INFERENCE_URL,
        api_key=os.environ.get("API_KEY", "dummy-key-for-testing")
    )

    messages = [
        {
            'role': 'system',
            'content': f'{REPO_SELECTION_PROMPT}'
        },
        {
            'role': 'user',
            'content': f'JOB CALL\n{json.dumps(job_call)}\n\nREPOSITORIES\n{json.dumps(repo_data)}'
        }
    ]

    completion_args = {
        'model': WRITER_MODEL,
        'messages': messages,
    }

    try:
        response = client.chat.completions.create(**completion_args)

    except Exception as e:
        response = None
        logger.error('Error during job summarization API call: %s', e)

    if response is not None:
        response = response.choices[0].message.content
        response = ast.literal_eval(response)

    # Now use the repository selection response to filter the repositories
    selected_repos = [
        repo for repo in github_repositories if repo['name'] in response
    ]

    return selected_repos


def _write_projects_section(project_repos: list, job_call: dict) -> str:
    """
    Write the projects section of the resume based on selected GitHub repositories.

    Args:
        project_repos (list): List of relevant GitHub repositories.
        job_call (dict): Extracted/summarized job call information.

    Returns:
        str: Formatted projects section for the resume.
    """

    logger = logging.getLogger(f'{__name__}._write_projects_section')

    # Let the model select the most relevant repositories based on the job call
    client = OpenAI(
        base_url=INFERENCE_URL,
        api_key=os.environ.get("API_KEY", "dummy-key-for-testing")
    )

    messages = [
        {
            'role': 'system',
            'content': f'{PROJECTS_SECTION_PROMPT}'
        },
        {
            'role': 'user',
            'content': (f'JOB CALL\n{json.dumps(job_call)}\n\n' + 
                f'REPOSITORIES\n{json.dumps(project_repos)}')
        }
    ]

    completion_args = {
        'model': WRITER_MODEL,
        'messages': messages,
    }

    try:
        response = client.chat.completions.create(**completion_args)

    except Exception as e:
        response = None
        logger.error('Error during job summarization API call: %s', e)

    if response is not None:
        response = response.choices[0].message.content

    return response