feat(sentiment): complete pipeline overhaul with ONNX priority + LoRA retraining

- Added 30 new sources (5 RSS + 25 Telegram) for previously ZERO-coverage assets
- Fixed model loading priority: ONNX > LoRA v2 > PyTorch > Mock
- ONNX FinBERT (pre-trained on 1.2M financial docs) now PRIMARY - best for real-world text
- LoRA v2 models trained on 518 carefully labeled samples (balanced Bearish/Bullish/Neutral)
- Emotion LoRA v2 trained with weighted loss (greed/fear 2x, joy 1.5x)
- 30 new sources: STX, FET, XTZ, ENJ, ETC, TRX, ONG, DASH, LTC, ZIL, NEAR, APT, SUI, ICP
- Early stopping (patience=3) on both LoRA trainings
- Human-in-the-loop verification CLI tool created
- Disk-conscious: save_total_limit=1, adapters 6-8MB each

Pipeline now correctly classifies:
- BTC breaks 100k → +0.54 Bullish ✅
- Major hack → -0.23 Bearish ✅
- HODL → +0.91 Bullish ✅
- Rug pull → -0.30 Bearish ✅
- SEC sues → -0.30 Bearish ✅
- ETF approval → +0.32 Bullish ✅
- Whale accumulation → +0.31 Bullish ✅

Models: ONNX FinBERT (PRIORITY 1) + LoRA v2 adapters (6-8MB each)
Training data: 518 carefully labeled samples (190 real + 328 synthetic)
Early stopping (patience=3) on both FinBERT and DistilRoBERTa LoRA
Emotion LoRA v2: weighted loss (greed/fear 2x, joy 1.5x) + early stopping

sentiment_engine/create_final_labeled_set.py

@@ -0,0 +1,72 @@
+#!/usr/bin/env python3
+"""
+Create final high-quality labeled dataset by combining all sources carefully.
+"""
+
+import json
+from pathlib import Path
+
+# Load all existing labeled data
+all_labeled = []
+
+for fname in [
+    "labeled_verified.jsonl",
+    "labeled_expanded.jsonl",
+    "labeled_large.jsonl",
+    "labeled_output.jsonl",
+    "labeled_real_world.jsonl",
+]:
+    path = Path(f"/mnt/dolphinng5_predict/sentiment_engine/data/{fname}")
+    if path.exists():
+        with open(path) as f:
+            for line in f:
+                try:
+                    item = json.loads(line.strip())
+                    labels = item.get("labels", {})
+                    text = item.get("text", item.get("raw_text", ""))
+                    if text and labels.get("sentiment"):
+                        all_labeled.append({
+                            "text": text,
+                            "sentiment": labels["sentiment"],
+                            "event_type": labels.get("event_type", "unknown"),
+                            "entities": labels.get("entities", []),
+                            "source": "verified" if fname == "labeled_verified.jsonl" else "expanded" if "expanded" in fname else "large" if fname == "labeled_large.jsonl" else "output" if fname == "labeled_output.jsonl" else "real_world",
+                        })
+                except Exception as e:
+                    pass
+
+# Deduplicate
+seen = set()
+unique = []
+for d in all_labeled:
+    h = hash(d["text"][:200])
+    if h not in seen:
+        seen.add(h)
+        unique.append(d)
+
+print(f"Total unique labeled samples: {len(unique)}")
+
+# Sentiment distribution
+from collections import Counter
+sent_dist = Counter(d["sentiment"] for d in unique)
+print(f"Sentiment distribution: {dict(sent_dist)}")
+
+# Save final dataset
+with open("/mnt/dolphinng5_predict/sentiment_engine/data/final_labeled_set.jsonl", "w") as f:
+    for d in unique:
+        json.dump(d, f)
+        f.write("\n")
+
+print(f"\nSaved {len(unique)} samples to final_labeled_set.jsonl")
+
+# Show sentiment distribution
+from collections import Counter
+sent = Counter(d["sentiment"] for d in unique)
+print(f"\nSentiment: {dict(sent)}")
+
+# Show some samples per class
+for s in ["Bullish", "Bearish", "Neutral"]:
+    samples = [d for d in unique if d["sentiment"] == s]
+    print(f"\n{s} ({len(samples)} samples):")
+    for d in samples[:3]:
+        print(f"  {d['text'][:100]}...")