fix: WAL mode for concurrent reads, skipped stats, anti-repetition prompts

database.py: enable PRAGMA journal_mode=WAL + synchronous=NORMAL so
  /status reads from concurrent connections see committed data without
  blocking behind the scraper's writes; add 'skipped' to get_session_stats

bot.py: show skipped count in fmt_progress and cmd_status; use 'or 0'
  to guard against NULL from SUM(); label active research in /status

processor.py: raise generate() temperature default to 0.7 + add
  repeat_penalty=1.15/repeat_last_n=128 to Ollama options to stop
  qwen2.5:3b from looping; scoring prompt keeps temperature=0.1

generator.py: rewrite all prompts with explicit "NEVER repeat"
  constraints and distinct-content rules per section; podcast prompt
  now asks for spoken-word style (no formal headers); reduce thread
  to 12-18 tweets (was 15-25) to fit model context; pass temperature=0.7

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

src/bot/bot.py

@@ -34,14 +34,15 @@ def is_authorized(user_id: int) -> bool:
 
 
 def fmt_progress(iteration: int, total: int, new: int, stats: dict) -> str:
-    scraped = stats.get("scraped", 0)
-    failed = stats.get("failed", 0)
-    pending = stats.get("pending", 0)
+    scraped = stats.get("scraped") or 0
+    failed  = stats.get("failed")  or 0
+    pending = stats.get("pending") or 0
+    skipped = stats.get("skipped") or 0
     return (
         f"🔄 *Iteration {iteration}*\n"
         f"📚 Sources found: `{total}`\n"
-        f"✅ Scraped: `{scraped}` | ❌ Failed: `{failed}` | ⏳ Pending: `{pending}`\n"
-        f"🆕 New this round: `{new}`"
+        f"✅ Scraped: `{scraped}` | ⏭️ Skipped: `{skipped}` | ❌ Failed: `{failed}` | ⏳ Pending: `{pending}`\n"
+        f"🆕 New URLs this round: `{new}`"
     )
 
 
@@ -213,13 +214,14 @@ async def cmd_status(update: Update, ctx: ContextTypes.DEFAULT_TYPE):
             f"📝 Topic: `{session['topic']}`\n"
             f"🔁 Status: `{session['status']}`\n"
             f"🔢 Iterations: `{session.get('iterations', 0)}`\n"
-            f"📚 Total sources: `{stats.get('total', 0)}`\n"
-            f"✅ Scraped: `{stats.get('scraped', 0)}`\n"
-            f"❌ Failed: `{stats.get('failed', 0)}`\n"
-            f"⏳ Pending: `{stats.get('pending', 0)}`\n"
+            f"📚 Total sources: `{stats.get('total') or 0}`\n"
+            f"✅ Scraped: `{stats.get('scraped') or 0}`\n"
+            f"⏭️ Skipped: `{stats.get('skipped') or 0}`\n"
+            f"❌ Failed: `{stats.get('failed') or 0}`\n"
+            f"⏳ Pending: `{stats.get('pending') or 0}`\n"
             f"💬 Chunks: `{session.get('total_chunks', 0)}`\n"
             f"📖 Words: `{session.get('total_words', 0):,}`\n"
-            f"{'🟢 Active' if is_active else '⚫ Idle'}",
+            f"{'🟢 Active — stats update each iteration' if is_active else '⚫ Idle'}",
             parse_mode=ParseMode.MARKDOWN
         )
     finally: