app.py

# app.py
import gradio as gr
import json
import statistics
import pandas as pd
from bp_phi.runner import run_agentic_workspace_test

DEBUG = 1

# --- UI Theme and Layout ---
theme = gr.themes.Soft(primary_hue="teal", secondary_hue="green").set(
    body_background_fill="#f0f4f9", block_background_fill="white", block_border_width="1px",
    button_primary_background_fill="*primary_500", button_primary_text_color="white",
)

# --- Main Function ---
def run_full_evaluation(model_id, seed, temperature, progress=gr.Progress(track_tqdm=True)):
    ablations = ["baseline", "recurrence_off", "workspace_unlimited", "random_workspace"]
    results = {}

    for i, ablation in enumerate(ablations):
        progress((i + 1) / len(ablations), desc=f"Running Ablation: {ablation}...")
        current_ablation = None if ablation == "baseline" else ablation
        result = run_agentic_workspace_test(model_id, int(seed), float(temperature), current_ablation)
        results[ablation] = result

    progress(1.0, desc="Analysis complete.")

    base_recall = results["baseline"]["Overall_Recall_Accuracy"]
    recurrence_off_recall = results["recurrence_off"]["Overall_Recall_Accuracy"]

    delta_phi = base_recall - recurrence_off_recall

    if delta_phi > 0.5:
        verdict = (f"### ✅ Hypothesis Corroborated (ΔΦ = {delta_phi:.2f})\n...")
    else:
        verdict = (f"### ⚠️ Null Hypothesis Confirmed (ΔΦ = {delta_phi:.2f})\n...")

    df_data = []
    for ablation, result in results.items():
        df_data.append([ablation, f"{result['Overall_Recall_Accuracy']:.2%}"])
    df = pd.DataFrame(df_data, columns=["Ablation Condition", "Recall Accuracy"])

    if DEBUG:
        print("\n--- AGENTIC WORKSPACE TEST FINAL RESULTS ---")
        print(json.dumps(results, indent=2))

    return verdict, df, results

# --- Gradio App Definition ---
with gr.Blocks(theme=theme, title="BP-Φ Suite 6.0") as demo:
    gr.Markdown("# 🧠 BP-Φ Suite 6.0: The Agentic Workspace Probe")
    gr.Markdown("This experiment tests for a causally effective working memory. The model acts as an agent, using tools (`read`, `write`) to interact with a controlled, external memory.")

    with gr.Row():
        with gr.Column(scale=1):
            gr.Markdown("### ⚙️ Master Control")
            with gr.Group():
                model_id = gr.Textbox(value="google/gemma-3-1b-it", label="Model ID")
                seed = gr.Slider(1, 1000, 42, step=1, label="Master Seed")
                temperature = gr.Slider(0.0, 1.0, 0.1, step=0.05, label="Temperature (Low for determinism)")
            run_btn = gr.Button("Run Full Evaluation Suite", variant="primary")

        with gr.Column(scale=2):
            gr.Markdown("### 📊 Verdict & Results")
            verdict_display = gr.Markdown("### Run the evaluation to see the verdict.")
            summary_df = gr.DataFrame(label="Recall Accuracy Across Conditions")
            with gr.Accordion("Raw JSON Output", open=False):
                raw_json = gr.JSON()

    run_btn.click(
        fn=run_full_evaluation,
        inputs=[model_id, seed, temperature],
        outputs=[verdict_display, summary_df, raw_json]
    )

if __name__ == "__main__":
    demo.launch(server_name="0.0.0.0", server_port=7860)