Upload 2 files

README.md

@@ -51,9 +51,10 @@ Nigerian English, Akan, Swahili, Nigerian Pidgin, … add more any time).
 
 | Variable | Default | Purpose |
 |----------|---------|---------|
-| `MOS_DATA_DIR` | `./data` | Where the SQLite DB, audio, and exports live. Point at your persistent mount (e.g. `/data` on a Space bucket). |
+| `MOS_DATA_DIR` | `./data` | **Persistent** location for audio files, exports, and the DB backup. Point at your bucket mount (e.g. `/data`). |
+| `MOS_LOCAL_DIR` | system temp `/…/mos_live` | Fast **local** disk where the live SQLite DB runs. It is backed up to `MOS_DATA_DIR` after every change and restored on startup. Usually leave as default. |
 | `ADMIN_CODE` | `plotweaver-admin` | Entered on the signup form to create an admin account. **Override this.** |
-| `MOS_JOURNAL_MODE` | `DELETE` | SQLite journal mode. Leave as `DELETE` on a bucket/network mount; set `WAL` only on a real local disk for extra concurrency. |
+| `MOS_SECRET` | derived from `ADMIN_CODE` | Secret used to sign browser session tokens (keeps a refreshed page logged in). Set a stable value in production. |
 | `PORT` | `7860` | Port the app binds to. |
 
 ---
@@ -105,11 +106,14 @@ for the older fixed `/data` storage tier).
 Notes:
 - The app already calls `launch(allowed_paths=[MOS_DATA_DIR])`, so Gradio is permitted to serve the
   audio files stored on the bucket. Without this, the audio player can't load clips from `/data`.
-- Buckets are object storage mounted as a filesystem (FUSE). SQLite's **WAL** mode relies on shared
-  memory that doesn't work on such mounts, which is why the default journal mode is `DELETE`. At a
-  few dozen reviewers this is comfortable; the only risk is a small chance of DB corruption if the
-  Space is killed mid-write. For a bulletproof setup, keep the DB on local disk and sync periodic
-  backups to the bucket (not built in — easy to add if you need it).
+- **Database on buckets:** the live SQLite database does **not** run directly on the bucket, because
+  object-store/FUSE mounts don't provide reliable file locking and writes can silently fail to
+  appear on later reads (causing "my ratings/files disappeared"). Instead the live DB runs on fast
+  local disk (`MOS_LOCAL_DIR`) and is atomically backed up to the bucket (`MOS_DATA_DIR/mos.db`)
+  after every change, then restored on startup. Audio files live on the bucket (static, write-once,
+  no locking issues). This survives Space restarts as long as the bucket stays mounted.
+- **Staying logged in:** a signed token is stored in the browser (`gr.BrowserState`) so a page
+  refresh keeps you signed in. Set a stable `MOS_SECRET` in production.
 
 ### Self-hosted (AlmaLinux / AWS, behind nginx)
 

app.py

@@ -28,9 +28,11 @@ The effective admin code is printed to the logs on startup.
 
 import os
 import re
+import hmac
 import sqlite3
 import hashlib
 import secrets
+import tempfile
 import datetime as dt
 import shutil
 
@@ -40,15 +42,75 @@ import gradio as gr
 # --------------------------------------------------------------------------- #
 # Configuration
 # --------------------------------------------------------------------------- #
+# DATA_DIR is the *persistent* location (e.g. a Hugging Face Storage Bucket at
+# /data). Audio files and the database BACKUP live here.
 DATA_DIR = os.environ.get("MOS_DATA_DIR", os.path.join(os.path.dirname(os.path.abspath(__file__)), "data"))
 AUDIO_DIR = os.path.join(DATA_DIR, "audio")
 EXPORT_DIR = os.path.join(DATA_DIR, "exports")
-DB_PATH = os.path.join(DATA_DIR, "mos.db")
 ADMIN_CODE = os.environ.get("ADMIN_CODE", "plotweaver-admin")
 
-for d in (DATA_DIR, AUDIO_DIR, EXPORT_DIR):
+# The LIVE database runs on fast LOCAL disk. SQLite needs real POSIX file
+# locking, which FUSE/object-store mounts (like a bucket) do not provide
+# reliably — running it directly on the bucket causes writes to silently not
+# appear on later reads. So we keep the working DB local and atomically back it
+# up to the bucket after every change (and restore it on startup).
+LOCAL_DIR = os.environ.get("MOS_LOCAL_DIR") or os.path.join(tempfile.gettempdir(), "mos_live")
+DB_PATH = os.path.join(LOCAL_DIR, "mos.db")        # live (local disk)
+DB_BACKUP = os.path.join(DATA_DIR, "mos.db")       # persistent copy (bucket)
+
+for d in (DATA_DIR, AUDIO_DIR, EXPORT_DIR, LOCAL_DIR):
     os.makedirs(d, exist_ok=True)
 
+# Restore the live DB from the persistent backup on startup (first boot / after
+# the container is recycled), so prior data survives restarts.
+if os.path.abspath(DB_BACKUP) != os.path.abspath(DB_PATH) \
+        and os.path.exists(DB_BACKUP) and not os.path.exists(DB_PATH):
+    try:
+        shutil.copyfile(DB_BACKUP, DB_PATH)
+    except OSError:
+        pass
+
+# Secret used to sign browser session tokens (keeps a refreshed page logged in).
+SESSION_SECRET = os.environ.get("MOS_SECRET") or hashlib.sha256(
+    ("mos-session::" + ADMIN_CODE).encode()).hexdigest()
+
+
+def backup_db():
+    """Atomically copy the live DB to the persistent backup on the bucket."""
+    if os.path.abspath(DB_BACKUP) == os.path.abspath(DB_PATH):
+        return
+    try:
+        src = sqlite3.connect(DB_PATH)
+        dst = sqlite3.connect(DB_BACKUP)
+        with dst:
+            src.backup(dst)
+        src.close()
+        dst.close()
+    except Exception:  # noqa  — best-effort backup; never break a write
+        pass
+
+
+def make_token(user_id):
+    sig = hmac.new(SESSION_SECRET.encode(), str(user_id).encode(), hashlib.sha256).hexdigest()[:32]
+    return f"{user_id}.{sig}"
+
+
+def verify_token(token):
+    """Return the user_id if the signed token is valid and the user is active."""
+    if not token or "." not in str(token):
+        return None
+    uid_str, sig = str(token).rsplit(".", 1)
+    try:
+        uid = int(uid_str)
+    except ValueError:
+        return None
+    good = hmac.new(SESSION_SECRET.encode(), str(uid).encode(), hashlib.sha256).hexdigest()[:32]
+    if not hmac.compare_digest(sig, good):
+        return None
+    with get_conn() as conn:
+        row = conn.execute("SELECT id, is_active FROM users WHERE id=?", (uid,)).fetchone()
+    return uid if (row and row["is_active"]) else None
+
 # The 7 MOS criteria, in the order they appear on the evaluation form.
 # (db_column, display_label, short_definition)
 CRITERIA = [
@@ -178,6 +240,7 @@ def create_user(username, email, password, role="reviewer", language_ids=None):
         uid = cur.lastrowid
         for lid in (language_ids or []):
             conn.execute("INSERT OR IGNORE INTO user_languages (user_id, language_id) VALUES (?,?)", (uid, lid))
+    backup_db()
     return uid
 
 
@@ -221,6 +284,7 @@ def add_language(code, name):
             conn.execute("INSERT INTO languages (code, name, created_at) VALUES (?,?,?)", (code, name, now_iso()))
         except sqlite3.IntegrityError:
             raise ValueError(f"Language code '{code}' already exists.")
+    backup_db()
 
 
 def list_languages():
@@ -233,6 +297,7 @@ def set_user_languages(uid, language_ids):
         conn.execute("DELETE FROM user_languages WHERE user_id = ?", (uid,))
         for lid in language_ids:
             conn.execute("INSERT OR IGNORE INTO user_languages (user_id, language_id) VALUES (?,?)", (uid, lid))
+    backup_db()
 
 
 # --------------------------------------------------------------------------- #
@@ -256,6 +321,7 @@ def add_sample(language_id, src_path, sample_name=None, model_name="unspecified"
             (language_id, sample_name, (model_name or "unspecified").strip(), dst,
              1 if is_reference else 0, (transcript or "").strip(), now_iso()),
         )
+    backup_db()
 
 
 def list_samples(language_id=None):
@@ -279,12 +345,14 @@ def delete_sample(sample_id):
             except OSError:
                 pass
         conn.execute("DELETE FROM samples WHERE id = ?", (sample_id,))
+    backup_db()
 
 
 def set_sample_transcript(sample_id, transcript):
     with get_conn() as conn:
         conn.execute("UPDATE samples SET transcript = ? WHERE id = ?",
                      ((transcript or "").strip(), sample_id))
+    backup_db()
 
 
 def get_sample_transcript(sample_id):
@@ -309,6 +377,7 @@ def upsert_rating(user_id, sample_id, scores, comments=""):
             f"comments=excluded.comments, updated_at=excluded.updated_at",
             [user_id, sample_id, *vals, (comments or "").strip(), now_iso()],
         )
+    backup_db()
 
 
 def get_rating(user_id, sample_id):
@@ -418,8 +487,9 @@ def export_results(language_id):
 init_db()
 print("=" * 64)
 print("Plotweaver AI — TTS MOS Evaluation Platform")
-print(f"Data directory : {DATA_DIR}")
-print(f"Database       : {DB_PATH}")
+print(f"Persistent dir : {DATA_DIR}")
+print(f"Live database  : {DB_PATH}")
+print(f"DB backup      : {DB_BACKUP}")
 print(f"Admin code     : {ADMIN_CODE}  (use on signup to create an admin)")
 print("=" * 64)
 
@@ -459,6 +529,7 @@ with gr.Blocks(title="Plotweaver AI — TTS MOS Evaluation",
                css=CSS) as demo:
     session = gr.State(None)          # logged-in user session dict
     current_sample = gr.State(None)   # sample id currently being rated
+    auth_token = gr.BrowserState("")  # signed token persisted in the browser (survives refresh)
 
     gr.Markdown("# 🎧 Plotweaver AI — TTS MOS Evaluation", elem_id="app-title")
     gr.Markdown("Rate synthesised speech on 7 quality criteria, by language.", elem_id="app-sub")
@@ -613,10 +684,18 @@ with gr.Blocks(title="Plotweaver AI — TTS MOS Evaluation",
             # keep typed credentials so the user can correct them
             return (gr.update(), gr.update(), None, "❌ Invalid username or password.",
                     gr.update(), gr.update(), gr.update(), gr.update(),
-                    gr.update(), gr.update())
+                    gr.update(), gr.update(), gr.update(),
+                    gr.update(), gr.update(), gr.update(), gr.update(), gr.update())
         sess = user_session(user["id"])
         is_admin = sess["role"] == "admin"
         rl = reviewer_lang_choices(sess)
+        if is_admin:
+            lt, st, ut = _languages_table(), _samples_table(), _users_table()
+            dch = _sample_delete_choices()
+            du, tu = gr.update(choices=dch), gr.update(choices=dch)
+        else:
+            lt, st, ut = [], [], []
+            du, tu = gr.update(), gr.update()
         return (
             gr.update(visible=False),                       # auth_col
             gr.update(visible=True),                        # app_col
@@ -628,18 +707,15 @@ with gr.Blocks(title="Plotweaver AI — TTS MOS Evaluation",
             gr.update(choices=rl, value=None),              # rate_lang
             gr.update(value=""),                            # li_user  (clear)
             gr.update(value=""),                            # li_pw    (clear)
+            make_token(user["id"]),                         # auth_token (persist login)
+            lt, st, ut, du, tu,                             # admin tables + pickers
         )
 
-    li_btn.click(
-        do_login, [li_user, li_pw],
-        [auth_col, app_col, session, li_msg, greeting, reviewer_tabs, admin_panel,
-         rate_lang, li_user, li_pw],
-    )
-    li_pw.submit(  # allow Enter-to-login
-        do_login, [li_user, li_pw],
-        [auth_col, app_col, session, li_msg, greeting, reviewer_tabs, admin_panel,
-         rate_lang, li_user, li_pw],
-    )
+    LOGIN_OUTPUTS = [auth_col, app_col, session, li_msg, greeting, reviewer_tabs, admin_panel,
+                     rate_lang, li_user, li_pw, auth_token,
+                     langs_tbl, samples_tbl, users_tbl, del_sample, tr_sample]
+    li_btn.click(do_login, [li_user, li_pw], LOGIN_OUTPUTS)
+    li_pw.submit(do_login, [li_user, li_pw], LOGIN_OUTPUTS)  # Enter-to-login
 
     def do_signup(username, email, password, lang_id, code):
         role = "admin" if (code and code == ADMIN_CODE) else "reviewer"
@@ -657,8 +733,8 @@ with gr.Blocks(title="Plotweaver AI — TTS MOS Evaluation",
                  [su_msg, su_user, su_email, su_pw, su_lang, su_code])
 
     def do_logout():
-        return (gr.update(visible=True), gr.update(visible=False), None, "")
-    logout_btn.click(do_logout, None, [auth_col, app_col, session, greeting])
+        return (gr.update(visible=True), gr.update(visible=False), None, "", "")
+    logout_btn.click(do_logout, None, [auth_col, app_col, session, greeting, auth_token])
 
     # ---- Rating flow ----
     def load_samples_for_lang(sess, language_id):
@@ -843,6 +919,7 @@ with gr.Blocks(title="Plotweaver AI — TTS MOS Evaluation",
         with get_conn() as conn:
             conn.execute("UPDATE users SET role=?, is_active=? WHERE id=?",
                          (role, 1 if active == "yes" else 0, int(uid)))
+        backup_db()
         return f"✅ Updated user {int(uid)}.", _users_table()
     update_user_btn.click(admin_update_user, [session, promote_id, role_choice, active_choice],
                           [user_admin_msg, users_tbl])
@@ -863,12 +940,36 @@ with gr.Blocks(title="Plotweaver AI — TTS MOS Evaluation",
         return export_results(language_id)
     export_btn.click(admin_export, [session, res_lang], [res_file])
 
-    # Populate admin tables + sample pickers right after an admin logs in.
-    li_btn.click(lambda s: (_languages_table(), _samples_table(), _users_table(),
-                            gr.update(choices=_sample_delete_choices()),
-                            gr.update(choices=_sample_delete_choices()))
-                 if s and s["role"] == "admin" else ([], [], [], gr.update(choices=[]), gr.update(choices=[])),
-                 [session], [langs_tbl, samples_tbl, users_tbl, del_sample, tr_sample])
+    # Restore the session on page load (so a refresh keeps you signed in).
+    def restore_session(token):
+        uid = verify_token(token)
+        if not uid:
+            # stay logged out; leave the UI at its default (auth visible)
+            return (gr.update(), gr.update(), None, gr.update(), gr.update(), gr.update(),
+                    gr.update(), gr.update(), gr.update(), gr.update(), gr.update(), gr.update())
+        sess = user_session(uid)
+        is_admin = sess["role"] == "admin"
+        rl = reviewer_lang_choices(sess)
+        if is_admin:
+            lt, st, ut = _languages_table(), _samples_table(), _users_table()
+            dch = _sample_delete_choices()
+            du, tu = gr.update(choices=dch), gr.update(choices=dch)
+        else:
+            lt, st, ut = [], [], []
+            du, tu = gr.update(), gr.update()
+        return (
+            gr.update(visible=False),                       # auth_col
+            gr.update(visible=True),                        # app_col
+            sess,                                           # session
+            gr.update(value=f"Signed in as **{sess['username']}**  ·  {sess['role']}"),  # greeting
+            gr.update(visible=not is_admin),                # reviewer_tabs
+            gr.update(visible=is_admin),                    # admin_panel
+            gr.update(choices=rl, value=None),              # rate_lang
+            lt, st, ut, du, tu,                             # admin tables + pickers
+        )
+    demo.load(restore_session, [auth_token],
+              [auth_col, app_col, session, greeting, reviewer_tabs, admin_panel, rate_lang,
+               langs_tbl, samples_tbl, users_tbl, del_sample, tr_sample])
 
     # Refresh language-dependent choices on every page load, so newly added
     # languages appear in the signup form (and admin dropdowns) without a restart.