inference.py

"""
Inference Script Example
===================================
MANDATORY
- Before submitting, ensure the following variables are defined in your environment configuration:
    API_BASE_URL   The API endpoint for the LLM.
    MODEL_NAME     The model identifier to use for inference.
    HF_TOKEN       Your Hugging Face / API key.
    LOCAL_IMAGE_NAME The name of the local image to use for the environment if you are using from_docker_image()
                     method

- Defaults are set only for API_BASE_URL and MODEL_NAME 
    (and should reflect your active inference setup):
    API_BASE_URL = os.getenv("API_BASE_URL", "<your-active-endpoint>")
    MODEL_NAME = os.getenv("MODEL_NAME", "<your-active-model>")
    
- The inference script must be named `inference.py` and placed in the root directory of the project
- Participants must use OpenAI Client for all LLM calls using above variables

STDOUT FORMAT
- The script must emit exactly three line types to stdout, in this order:

    [START] task=<task_name> env=<benchmark> model=<model_name>
    [STEP]  step=<n> action=<action_str> reward=<0.00> done=<true|false> error=<msg|null>
    [END]   success=<true|false> steps=<n> score=<score> rewards=<r1,r2,...,rn>

  Rules:
    - One [START] line at episode begin.
    - One [STEP] line per step, immediately after env.step() returns.
    - One [END] line after env.close(), always emitted (even on exception).
    - reward and rewards are formatted to 2 decimal places.
    - done and success are lowercase booleans: true or false.
    - error is the raw last_action_error string, or null if none.
    - All fields on a single line with no newlines within a line.
    - Each tasks should return score in [0, 1]

  Example:
    [START] task=click-test env=miniwob model=Qwen3-VL-30B
    [STEP] step=1 action=click('123') reward=0.00 done=false error=null
    [STEP] step=2 action=fill('456','text') reward=0.00 done=false error=null
    [STEP] step=3 action=click('789') reward=1.00 done=true error=null
    [END] success=true steps=3 score=1.00 rewards=0.00,0.00,1.00
"""

import asyncio
import os
import textwrap
from typing import List, Optional
from urllib.parse import urlparse

from dotenv import load_dotenv
from openai import OpenAI

load_dotenv()  # Load environment variables from .env file

from molecular_Designer_Env.client import MolecularDesignerEnvEnv
from molecular_Designer_Env.models import MolecularDesignerEnvAction



IMAGE_NAME = os.getenv("IMAGE_NAME") # If you are using docker image 
BASE_URL = os.getenv("BASE_URL") # If connecting to deployed server
API_KEY = os.getenv("HF_TOKEN") or os.getenv("API_KEY")

API_BASE_URL = os.getenv("API_BASE_URL") or "https://router.huggingface.co/v1"
MODEL_NAME = os.getenv("MODEL_NAME") or "Qwen/Qwen2.5-72B-Instruct"
TASK_NAME = os.getenv("TASK_NAME", "easy")
BENCHMARK = os.getenv("BENCHMARK", "molecular_Designer_Env")
MAX_STEPS = 10
TEMPERATURE = 0.7
MAX_TOKENS = 150
SUCCESS_SCORE_THRESHOLD = 0.85  # normalized score in [0, 1]

# Replaced total max reward tracking since it's now dynamically evaluated up to 1.0 per task
MAX_TOTAL_REWARD = 1.0

SYSTEM_PROMPT = textwrap.dedent(
    """
    You are an expert medicinal chemist AI acting in a molecular design environment.
    Each turn you will receive feedback on a molecule you design.
    Your goal is to provide a valid SMILES string that maximizes the task's unique reward.
    Reply with exactly one SMILES string - no quotes, no prefixes, just the SMILES string (e.g. CCO).
    """
).strip()


def log_start(task: str, env: str, model: str) -> None:
    print(f"[START] task={task} env={env} model={model}", flush=True)


def log_step(step: int, action: str, reward: float, done: bool, error: Optional[str]) -> None:
    error_val = error if error else "null"
    done_val = str(done).lower()
    print(
        f"[STEP] step={step} action={action} reward={reward:.2f} done={done_val} error={error_val}",
        flush=True,
    )


def log_end(success: bool, steps: int, score: float, rewards: List[float]) -> None:
    rewards_str = ",".join(f"{r:.2f}" for r in rewards)
    print(f"[END] success={str(success).lower()} steps={steps} score={score:.3f} rewards={rewards_str}", flush=True)


def build_user_prompt(step: int, last_feedback: str, last_reward: float, history: List[str]) -> str:
    history_block = "\n".join(history[-4:]) if history else "None"
    return textwrap.dedent(
        f"""
        Step: {step}
        Last feedback: {last_feedback!r}
        Last reward: {last_reward:.3f}
        Previous steps history:
        {history_block}
        Generate your next SMILES string to improve your score. Follow the task's rules and constraints exactly. Target MW or LogP where applicable.
        """
    ).strip()

def get_model_message(client: OpenAI, step: int, last_feedback: str, last_reward: float, history: List[str]) -> str:
    user_prompt = build_user_prompt(step, last_feedback, last_reward, history)
    try:
        completion = client.chat.completions.create(
            model=MODEL_NAME,
            messages=[
                {"role": "system", "content": SYSTEM_PROMPT},
                {"role": "user", "content": user_prompt},
            ],
            temperature=TEMPERATURE,
            max_tokens=MAX_TOKENS,
            stream=False,
        )
        text = (completion.choices[0].message.content or "").strip()
        return text if text else "CCO"
    except Exception as exc:
        print(f"[DEBUG] Model request failed: {exc}", flush=True)
        return "CCO"


def normalize_base_url(base_url: Optional[str]) -> Optional[str]:
    """Normalize user-provided BASE_URL into an API runtime URL.

    If a Hugging Face repo page URL is provided (huggingface.co/spaces/user/space),
    convert it to the runtime domain (https://user-space.hf.space).
    """
    if not base_url:
        return base_url

    cleaned = base_url.strip().rstrip("/")
    parsed = urlparse(cleaned)

    # Handle Hugging Face repo page URL -> runtime URL used by API/WebSocket.
    if parsed.netloc == "huggingface.co":
        parts = [p for p in parsed.path.strip("/").split("/") if p]
        if len(parts) >= 3 and parts[0] == "spaces":
            owner, space = parts[1], parts[2]
            return f"https://{owner}-{space}.hf.space"

    # Avoid accidentally pointing at the web UI path.
    if cleaned.endswith("/web"):
        return cleaned[:-4]

    return cleaned


async def main() -> None:
    client = OpenAI(base_url=API_BASE_URL, api_key=API_KEY)
    runtime_base_url = normalize_base_url(BASE_URL)

    if runtime_base_url:
        env = MolecularDesignerEnvEnv(base_url=runtime_base_url)
    else:
        if not IMAGE_NAME:
            raise ValueError(
                "Set BASE_URL for deployed env, or IMAGE_NAME for local docker env."
            )
        env = await MolecularDesignerEnvEnv.from_docker_image(IMAGE_NAME)

    history: List[str] = []
    rewards: List[float] = []
    steps_taken = 0
    score = 0.0
    success = False

    log_start(task=TASK_NAME, env=BENCHMARK, model=MODEL_NAME)

    try:
        result = await asyncio.to_thread(env.reset) # Ensure async execution correctly maps
        last_feedback = result.observation.feedback
        last_reward = 0.0

        for step in range(1, MAX_STEPS + 1):
            if result.done:
                break

            message = get_model_message(client, step, last_feedback, last_reward, history)

            result = await asyncio.to_thread(env.step, MolecularDesignerEnvAction(smiles=message))
            obs = result.observation

            reward = result.reward or 0.0
            done = result.done
            error = None

            rewards.append(reward)
            steps_taken = step
            last_feedback = obs.feedback
            last_reward = reward

            log_step(step=step, action=message, reward=reward, done=done, error=error)

            history.append(f"Step {step}: {message!r} -> reward {reward:+.3f}")

            if done:
                break

        score = max(rewards) if rewards else 0.0
        score = min(max(score, 0.0), 1.0)  # clamp to [0, 1]
        success = score >= SUCCESS_SCORE_THRESHOLD

    finally:
        try:
            env.close()
        except Exception as e:
            print(f"[DEBUG] env.close() error (container cleanup): {e}", flush=True)
        log_end(success=success, steps=steps_taken, score=score, rewards=rewards)


if __name__ == "__main__":
    asyncio.run(main())