Delete app.py

app.py

@@ -1,326 +0,0 @@
-"""
-app.py — BERTopic Topic Modelling Agent UI.
-
-Three UX features:
-    1. Phase banner — large prominent display of current B&C phase
-    2. Dynamic prompts — phase-appropriate suggested next actions
-    3. Auto-populated review table — loads from tool checkpoint files
-
-9-column review table: #, Topic Label, Top Evidence, Sentences, Papers,
-Approve, Rename To, Move To, Reasoning.
-"""
-
-import gradio as gr
-import pandas as pd
-import json
-import os
-import re
-import tempfile
-from datetime import datetime
-from pathlib import Path
-from agent import run as agent_run
-
-THREAD_ID = f"bertopic-{datetime.now().strftime('%Y%m%d%H%M%S')}"
-
-REVIEW_COLS = [
-    "#", "Topic Label", "Top Evidence", "Sentences", "Papers",
-    "Approve", "Rename To", "Move To", "Reasoning",
-]
-
-EMPTY_TABLE = pd.DataFrame(
-    {"#": ["-"], "Topic Label": ["No results yet — run analysis first"],
-     "Top Evidence": [""], "Sentences": [""], "Papers": [""],
-     "Approve": [""], "Rename To": [""], "Move To": [""], "Reasoning": [""]},
-)
-
-PHASE_INFO = {
-    0: ("Getting started", "⬜⬜⬜⬜⬜⬜",
-        "Upload a CSV file, then click **Analyze my Scopus CSV** and press Send"),
-    1: ("Phase 1 — Familiarisation", "🟦⬜⬜⬜⬜⬜",
-        "Click **Run abstract analysis** or **Run title analysis** and press Send"),
-    2: ("Phase 2 — Initial Codes", "🟦🟦⬜⬜⬜⬜",
-        "Review clusters in the **Results table** below. Edit Approve / Rename / Move, "
-        "then click **Submit Review**"),
-    3: ("Phase 3 — Themes", "🟦🟦🟦⬜⬜⬜",
-        "Review merged themes. Edit the table, then click **Submit Review**"),
-    4: ("Phase 4 — Saturation", "🟦🟦🟦🟦⬜⬜",
-        "Review saturation metrics. Click **Submit Review** to confirm"),
-    5: ("Phase 5 — Naming", "🟦🟦🟦🟦🟦⬜",
-        "Review theme profiles. Edit names, then **Submit Review**"),
-    6: ("Phase 6 — Report", "🟦🟦🟦🟦🟦🟦",
-        "Review comparison and narrative. **Submit Review** to finalise"),
-}
-
-_path = lambda file: str(
-    (hasattr(file, "name") and file.name)
-    or (isinstance(file, str) and file)
-    or ""
-)
-_name = lambda file: os.path.basename(_path(file))
-
-
-def _extract_phase(text: str) -> int:
-    """Extract phase number from agent response. Returns 0 if not found."""
-    found = re.findall(r"Phase (\d)", str(text))
-    return int((found or ["0"])[0])
-
-
-def _phase_banner(num: int) -> str:
-    """Generate prominent phase banner with progress bar and next step."""
-    name, progress, instruction = PHASE_INFO.get(num, PHASE_INFO[0])
-    return (
-        f"## {progress}  {name}\n\n"
-        f"**NEXT STEP →** {instruction}"
-    )
-
-
-def _load_review_table(base_dir: str) -> pd.DataFrame:
-    """Load latest checkpoint file into the 9-column review table.
-
-    Scans base_dir for topic_labels.json, themes.json, taxonomy_alignment.json,
-    summaries.json. Loads the most recently modified one and formats it.
-    Returns EMPTY_TABLE if nothing found.
-    """
-    base = Path(str(base_dir or "/tmp/nonexistent_dir_placeholder"))
-    candidates = (
-        base_dir and base.exists() and sorted(
-            (
-                list(base.glob("topic_labels.json"))
-                + list(base.glob("themes.json"))
-                + list(base.glob("taxonomy_alignment.json"))
-                + list(base.glob("summaries.json"))
-            ),
-            key=lambda p: p.stat().st_mtime,
-            reverse=True,
-        )
-    ) or []
-
-    latest = (candidates[:1] or [None])[0]
-    return (latest and [_format_checkpoint(latest)] or [EMPTY_TABLE.copy()])[0]
-
-
-def _format_checkpoint(path) -> pd.DataFrame:
-    """Format a checkpoint JSON file into review table rows.
-
-    Merges data from multiple checkpoint files when available:
-    topic_labels.json has labels but no sizes — summaries.json has sizes.
-    """
-    raw = json.loads(Path(path).read_text())
-    base = Path(path).parent
-
-    data = (isinstance(raw, dict) and raw.get("clusters", raw.get("per_theme", []))) or \
-           (isinstance(raw, list) and raw) or []
-
-    summaries_data = {}
-    summaries_path = base / "summaries.json"
-    summaries_raw = (
-        summaries_path.exists() and json.loads(summaries_path.read_text()) or {}
-    )
-    summaries_list = (
-        isinstance(summaries_raw, dict) and summaries_raw.get("clusters", [])
-    ) or (isinstance(summaries_raw, list) and summaries_raw) or []
-    list(map(
-        lambda s: summaries_data.update({s.get("topic_id", -999): s}),
-        summaries_list,
-    ))
-
-    def _row(item: dict) -> dict:
-        """Map one JSON item to review table columns, merging summaries data."""
-        tid = item.get("topic_id", item.get("theme_id", 0))
-        summary = summaries_data.get(tid, {})
-        return {
-            "#":            tid,
-            "Topic Label":  item.get("label", item.get("theme_label", "")),
-            "Top Evidence":  str(
-                item.get("representative", "")
-                or summary.get("representative", "")
-                or item.get("notes", "")
-            )[:150],
-            "Sentences":    item.get("size", 0) or summary.get("size", 0)
-                            or item.get("total_papers", 0),
-            "Papers":       item.get("size", 0) or summary.get("size", 0)
-                            or item.get("total_papers", 0),
-            "Approve":      "Yes",
-            "Rename To":    "",
-            "Move To":      "",
-            "Reasoning":    str(item.get("rationale", item.get("notes", ""))),
-        }
-
-    rows = list(map(_row, data[:200]))
-    return (rows and [pd.DataFrame(rows, columns=REVIEW_COLS)] or [EMPTY_TABLE.copy()])[0]
-
-
-def on_file_upload(file):
-    """Extract CSV stats and store base directory."""
-    path = _path(file)
-    result = (not path) and ("Upload a CSV to begin.", "", _phase_banner(0))
-    return result or _do_file_upload(path, file)
-
-
-def _do_file_upload(path: str, file) -> tuple:
-    """Actual file processing after path validation."""
-    df = pd.read_csv(path)
-    rows, cols = df.shape
-    base = str(Path(path).parent)
-    info = (
-        f"**Loaded:** `{_name(file)}`\n\n"
-        f"**Shape:** {rows:,} rows x {cols} columns\n\n"
-        f"**Columns:** {', '.join(df.columns[:6].tolist())}\n\n"
-        f"*Click a prompt below and press Send to begin.*"
-    )
-    return info, base, _phase_banner(1)
-
-
-def on_send(user_msg, history, file, base_dir):
-    """Pass user message to agent. Update phase banner and review table."""
-    msg = (user_msg or "").strip() or "help"
-    csv_tag = f"[CSV: {_path(file)}]\n" * bool(file)
-
-    history = list(history or [])
-    history.append({"role": "user", "content": msg})
-    history.append({"role": "assistant", "content": "Thinking..."})
-    yield history, "", gr.skip(), gr.skip(), gr.skip()
-
-    reply = agent_run(csv_tag + msg, thread_id=THREAD_ID)
-    history[-1] = {"role": "assistant", "content": reply}
-
-    phase = _extract_phase(reply)
-    banner = _phase_banner(phase)
-    table = _load_review_table(base_dir)
-
-    yield history, "", banner, table, base_dir
-
-
-def on_submit_review(table_df, history, base_dir):
-    """Serialise review table edits to agent."""
-    history = list(history or [])
-    edits = table_df.to_json(orient="records", indent=2)
-
-    history.append({"role": "user", "content": "[REVIEW SUBMITTED]"})
-    history.append({"role": "assistant", "content": "Processing review..."})
-
-    reply = agent_run(
-        "Reviewer submitted table edits.\n\n"
-        f"```json\n{edits}\n```\n\n"
-        "Process: Approve/Reject decisions, Rename To values, "
-        "Move To reassignments (call reassign_sentences if moves exist), "
-        "Reasoning notes. Then check STOP gates and proceed.",
-        thread_id=THREAD_ID,
-    )
-    history[-1] = {"role": "assistant", "content": reply}
-
-    phase = _extract_phase(reply)
-    return history, _phase_banner(phase), _load_review_table(base_dir)
-
-
-def on_download(table_df, history):
-    """Export review CSV and chat TXT."""
-    csv_tmp = tempfile.NamedTemporaryFile(delete=False, suffix=".csv", prefix="review_")
-    table_df.to_csv(csv_tmp.name, index=False)
-
-    txt_tmp = tempfile.NamedTemporaryFile(delete=False, suffix=".txt", prefix="chat_")
-    txt_tmp.write(
-        "\n\n".join(
-            list(map(
-                lambda m: f"{m.get('role', '').upper()}: {m.get('content', '')}",
-                history or [],
-            ))
-        ).encode("utf-8")
-    )
-    txt_tmp.close()
-    return [csv_tmp.name, txt_tmp.name]
-
-
-with gr.Blocks(title="BERTopic Agent") as demo:
-
-    base_dir_state = gr.State(value="")
-
-    gr.Markdown("# BERTopic Modelling Agent")
-    gr.Markdown(
-        "**Braun & Clarke 6-Phase Thematic Analysis** "
-        "| 10 Tools | 6 STOP Gates | Cosine Agglomerative Clustering"
-    )
-
-    phase_banner = gr.Markdown(value=_phase_banner(0))
-
-    gr.Markdown("---\n### Section 1 — Data input")
-    with gr.Row():
-        with gr.Column(scale=3):
-            file_input = gr.File(
-                label="Upload Scopus CSV",
-                file_types=[".csv"],
-                file_count="single",
-            )
-        with gr.Column(scale=5):
-            file_info = gr.Markdown("Upload a CSV to begin.")
-
-    gr.Markdown("---\n### Section 2 — Agent conversation")
-    chatbot = gr.Chatbot(label="BERTopic Agent", height=200)
-    with gr.Row():
-        msg_box = gr.Textbox(
-            placeholder="Type a message or click a prompt below, then press Send",
-            show_label=False, scale=7, lines=1,
-        )
-        send_btn = gr.Button("Send", variant="primary", scale=1)
-
-    gr.Examples(
-        examples=[
-            "Analyze my Scopus CSV",
-            "Run abstract analysis",
-            "Run title analysis",
-            "Proceed to next phase",
-            "Show corpus statistics",
-        ],
-        inputs=msg_box,
-        label="Quick prompts (click to fill, then press Send)",
-    )
-
-    gr.Markdown("---\n### Section 3 — Results (auto-populated from tool outputs)")
-    gr.Markdown(
-        "This table fills automatically when the agent runs tools. "
-        "Edit **Approve**, **Rename To**, **Move To**, **Reasoning** columns, "
-        "then click **Submit Review**."
-    )
-    review_table = gr.Dataframe(
-        value=EMPTY_TABLE,
-        headers=REVIEW_COLS,
-        datatype=["number", "str", "str", "number", "number",
-                  "str", "str", "str", "str"],
-        column_count=(9, "fixed"),
-        interactive=True,
-        wrap=True,
-        max_height=400,
-    )
-    with gr.Row():
-        clear_btn = gr.Button("Clear table", variant="secondary", scale=2)
-        sub_btn = gr.Button("Submit Review", variant="primary", scale=4)
-
-    with gr.Accordion("Download", open=False):
-        dl_btn = gr.Button("Generate downloads", variant="primary")
-        dl_files = gr.File(label="Downloads", file_count="multiple",
-                          interactive=False)
-
-    file_input.change(
-        on_file_upload,
-        inputs=[file_input],
-        outputs=[file_info, base_dir_state, phase_banner],
-    )
-    send_btn.click(
-        on_send,
-        inputs=[msg_box, chatbot, file_input, base_dir_state],
-        outputs=[chatbot, msg_box, phase_banner, review_table, base_dir_state],
-    )
-    msg_box.submit(
-        on_send,
-        inputs=[msg_box, chatbot, file_input, base_dir_state],
-        outputs=[chatbot, msg_box, phase_banner, review_table, base_dir_state],
-    )
-    clear_btn.click(lambda: EMPTY_TABLE.copy(), outputs=[review_table])
-    sub_btn.click(
-        on_submit_review,
-        inputs=[review_table, chatbot, base_dir_state],
-        outputs=[chatbot, phase_banner, review_table],
-    )
-    dl_btn.click(on_download, inputs=[review_table, chatbot], outputs=[dl_files])
-
-demo.launch(ssr_mode=False, theme=gr.themes.Soft())