app.py

import logging
log = logging.getLogger(__name__)

from typing import Any

import gradio as gr
from PIL import Image

# from src import config
from src.agents.mise_en_place import identify_ingredients
# from src.agents.progress_validator import validate
# from src.agents.recipe_planner import plan_recipe, propose_dishes
# from src.data.nutrition import compute_nutrition
# from src.pipeline import Recipe
from src.ui.components import (
    DishOptions,
    IngredientChips,
    NutritionGrid,
    RecipeHero,
    StepCard,
    VerdictBadge,
    recipe_to_state,
)
from src.ui.theme import CSS, theme

def on_propose(fridge_image: Image.Image | None, state: dict | None) -> tuple[str, str, list[str], dict]:
    """Photo → ingredients → 3 dish options."""
    state = state or {}
    ingredients = identify_ingredients(fridge_image)
    # options = propose_dishes(ingredients)

    # state.update({
    #     "ingredients_have": ingredients,
    #     "ingredients_missing": [],
    #     "options": [o.model_dump() for o in options],
    # })
    chips_html = IngredientChips.render({"have": ingredients, "missing": []})
    log.info(ingredients)
    # options_html = DishOptions.render({"options": state["options"]})
    # radio_choices = [o.name for o in options]
    # return chips_html, options_html, gr.update(choices=radio_choices, value=radio_choices[0] if radio_choices else None), state
    return chips_html



# ----------------
# UI definition
# ----------------
def build_ui() -> gr.Blocks:
    initial_state: dict[str, Any] = {}

    with gr.Blocks(title="Cook With Me") as demo:
        gr.Markdown(
            "# 🍲 Cook With Me\n"
            "_A multimodal sous-chef. See it. Plan it. Show it. Cook it._"
        )

        state = gr.State(initial_state)

        with gr.Tabs():
            # --- Tab 1: Cook ------------------------------------------------
            with gr.Tab("Cook"):
                with gr.Row():
                    with gr.Column(scale=1):
                        fridge_input = gr.Image(
                            label="📸 Photo of your fridge or pantry",
                            type="pil",
                            height=320,
                        )
                        propose_btn = gr.Button("What can I cook?", variant="primary")

                        gr.Markdown("### Ingredients I see")
                        chips = gr.HTML(IngredientChips.render({}))

                        gr.Markdown("### Pick a dish")
                        options = gr.HTML(DishOptions.render({}))
                        dish_radio = gr.Radio(choices=[], label="Choose one", interactive=True)

                        with gr.Accordion("Generation options", open=False):
                            illustrate_chk = gr.Checkbox(value=False, label="Render step images (FLUX, slow on CPU)")
                            narrate_chk = gr.Checkbox(value=False, label="Generate voice narration (VoxCPM2)")

                        cook_btn = gr.Button("Build recipe", variant="primary")

                    with gr.Column(scale=2):
                        hero = gr.HTML(RecipeHero.render({}))
                        steps_panel = gr.HTML(StepCard.render({}))
                        nutrition_panel = gr.HTML(NutritionGrid.render({"nutrition": {}}))

            # --- Tab 2: Check Progress -------------------------------------
            with gr.Tab("Check Progress"):
                gr.Markdown("Upload a photo of your pan or plate; the same vision model that planned your recipe will compare it against the target step.")
                with gr.Row():
                    with gr.Column():
                        step_idx = gr.Number(value=1, precision=0, label="Active step #")
                        progress_input = gr.Image(label="📸 Your pan / plate", type="pil", height=320)
                        validate_btn = gr.Button("How am I doing?", variant="primary")
                    with gr.Column():
                        verdict_panel = gr.HTML(VerdictBadge.render({}))
                        verdict_audio = gr.Audio(label="Tip (voice)", autoplay=False)

            # --- Tab 3: About ----------------------------------------------
            with gr.Tab("About"):
                gr.Markdown(
                    """
                    ### Models
                    - **Vision** — `openbmb/MiniCPM-V-4_6-gguf` via `llama-cpp-python` (~4.6B)
                    - **Planner** — `openbmb/MiniCPM-V-4-gguf` via `llama-cpp-python` (~4B)
                    - **Illustrator** — `black-forest-labs/FLUX.2-klein-9B` via `diffusers` (9B)
                    - **Narrator** — `openbmb/VoxCPM2` via `transformers` (~1B)
                    - **Retrieval** — `sentence-transformers/all-MiniLM-L6-v2` (22M)
                    **Total ≈ 18.6B params** (≤ 32B requirement ✓).
                    ### Pipeline
                    ```
                    Fridge photo → Vision → ingredients
                                            │
                                            ▼
                                    Planner (+ Kaggle retrieval) → Recipe JSON
                                            │
                                            ▼
                                    Illustrator (FLUX) → hero + per-step images
                                            │
                                            ▼
                                    Narrator (VoxCPM2) → MP3 per step
                                            │
                                            ▼
                    Progress photo → Validator (same vision model) → go|wait|fix
                    ```
                    ### Badges targeted
                    ✓ Llama Champion · ✓ Well-Tuned · ✓ Off-Brand · ✓ Sharing is Caring · ✓ Field Notes
                    """
                )

        # Wire callbacks ----------------------------------------------------
        propose_btn.click(
            fn=on_propose,
            inputs=[fridge_input, state],
            # outputs=[chips, options, dish_radio, state],
            outputs=[chips],
        )
        # cook_btn.click(
        #     fn=on_pick_dish,
        #     inputs=[state, dish_radio, illustrate_chk, narrate_chk],
        #     outputs=[hero, steps_panel, nutrition_panel, chips, state],
        # )
        # validate_btn.click(
        #     fn=on_validate,
        #     inputs=[state, step_idx, progress_input],
        #     outputs=[verdict_panel, verdict_audio],
        # )

    return demo


if __name__ == "__main__":
    demo = build_ui()
    demo.launch(
        server_name="0.0.0.0",
        server_port=int(__import__("os").environ.get("PORT", 7860)),
        show_error=True,
        inbrowser=True,
        theme=theme, 
        css=CSS
    )