Fix demo mode: writable /data check, path resolution, load order

- config.py: verify /data is writable before using it (HF Spaces
without persistent storage has /data but read-only)
- demo.py: use CONFIG_PATH/DB_PATH from config, load DB before
copying config to avoid early-exit race
- entrypoint.sh: always set DEMO_MODE when no API key, simpler logic

entrypoint.sh

@@ -5,18 +5,13 @@ PORT="${PORT:-8888}"
 
 echo "=== Research Intelligence ==="
 
-# Bootstrap demo data if no config exists and no API key set
-if [ -n "$SPACE_ID" ]; then
-    CONFIG_PATH="/data/config.yaml"
-else
-    CONFIG_PATH="config.yaml"
-fi
-
-if [ ! -f "$CONFIG_PATH" ] && [ -f "data/demo-data.json" ] && [ -z "$ANTHROPIC_API_KEY" ]; then
-    echo "No config found and no API key set — loading demo data..."
-    python -c "from src.demo import load_demo; load_demo()"
+# No API key → demo mode (load bundled data if needed)
+if [ -z "$ANTHROPIC_API_KEY" ]; then
+    if [ -f "data/demo-data.json" ]; then
+        python -c "from src.demo import load_demo; load_demo()" || true
+    fi
     export DEMO_MODE=1
-    echo "Demo mode active. Deploy locally with an API key for full functionality."
+    echo "Demo mode — no API key set. Deploy locally for full functionality."
 fi
 
 echo "Starting web server + scheduler on port ${PORT} ..."

src/config.py

@@ -37,7 +37,14 @@ DEMO_MODE = bool(os.environ.get("DEMO_MODE"))
 def _spaces_data_dir() -> Path:
     """Return /data on HF Spaces (persistent storage), otherwise local data/."""
     if IS_HF_SPACE and Path("/data").exists():
-        return Path("/data")
+        # Verify /data is actually writable (persistent storage enabled)
+        try:
+            test_file = Path("/data/.write_test")
+            test_file.touch()
+            test_file.unlink()
+            return Path("/data")
+        except OSError:
+            pass  # /data exists but not writable — no persistent storage
     return Path("data")
 
 

src/demo.py

@@ -10,7 +10,7 @@ log = logging.getLogger(__name__)
 
 def load_demo():
     """Load demo data into a fresh database and copy demo config."""
-    from src.config import IS_HF_SPACE, SPACES_DATA_DIR
+    from src.config import CONFIG_PATH, DB_PATH
 
     json_path = Path("data/demo-data.json")
     config_src = Path("data/demo-config.yaml")
@@ -19,44 +19,23 @@ def load_demo():
         log.warning("Demo data not found at %s", json_path)
         return
 
-    # Determine target paths
-    if IS_HF_SPACE:
-        config_dst = SPACES_DATA_DIR / "config.yaml"
-        db_path = SPACES_DATA_DIR / "researcher.db"
-    else:
-        config_dst = Path("config.yaml")
-        db_path = Path("data/researcher.db")
+    config_dst = CONFIG_PATH
+    db_path = DB_PATH
 
-    # Copy config
-    if config_src.exists() and not config_dst.exists():
-        config_dst.parent.mkdir(parents=True, exist_ok=True)
-        shutil.copy2(config_src, config_dst)
-        log.info("Demo config copied to %s", config_dst)
-
-    # Skip if DB already has data
-    if db_path.exists():
-        log.info("DB already exists at %s — skipping demo load", db_path)
+    # Skip if already set up
+    if config_dst.exists() or db_path.exists():
+        log.info("Config or DB already exists — skipping demo load")
         return
 
-    # Initialize DB with current schema
-    import os
-    os.environ["DB_PATH"] = str(db_path)
-
-    # Re-import to pick up new path
-    import importlib
-    import src.config
-    importlib.reload(src.config)
-
+    # Load DB first, then copy config
     from src.db import init_db, get_conn
     init_db()
 
-    # Load JSON
     data = json.loads(json_path.read_text())
     runs = data.get("runs", [])
     papers = data.get("papers", [])
 
     with get_conn() as conn:
-        # Insert runs
         for r in runs:
             conn.execute(
                 """INSERT OR IGNORE INTO runs (id, domain, started_at, finished_at,
@@ -66,7 +45,6 @@ def load_demo():
                  r["date_start"], r["date_end"], r["paper_count"], r["status"]),
             )
 
-        # Insert papers
         for p in papers:
             conn.execute(
                 """INSERT INTO papers (run_id, domain, arxiv_id, entry_id, title,
@@ -87,7 +65,12 @@ def load_demo():
                  p.get("s2_tldr"), p.get("s2_paper_id"), p.get("topics")),
             )
 
-        # Rebuild FTS index
         conn.execute("INSERT INTO papers_fts(papers_fts) VALUES('rebuild')")
 
     log.info("Demo data loaded: %d runs, %d papers into %s", len(runs), len(papers), db_path)
+
+    # Copy config last (entrypoint checks config existence to set DEMO_MODE)
+    if config_src.exists():
+        config_dst.parent.mkdir(parents=True, exist_ok=True)
+        shutil.copy2(config_src, config_dst)
+        log.info("Demo config written to %s", config_dst)