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/tests/unit/test_schemas_output.py

@@ -0,0 +1,147 @@
+"""Tests for output schemas"""
+
+import pytest
+from sentiment_engine.schemas.output import (
+    AssetSentiment, MarketSentiment, IndustrySentiment, SentimentOutput,
+    PumpDumpScore, VelocityMetrics, EventFlag
+)
+
+
+class TestPumpDumpScore:
+    """Tests for PumpDumpScore"""
+
+    def test_valid_score(self):
+        score = PumpDumpScore(
+            asset_id="BTC",
+            pump_score=75.0,
+            dump_score=15.0,
+            pump_confidence=0.8,
+            dump_confidence=0.7,
+            coordinating_sources=3,
+            last_update_ts=1234567890.0
+        )
+        assert score.asset_id == "BTC"
+        assert score.pump_score == 75.0
+
+    def test_bounds_check(self):
+        with pytest.raises(ValueError):
+            PumpDumpScore(
+                asset_id="BTC",
+                pump_score=150.0,  # > 100
+                dump_score=15.0,
+                pump_confidence=0.8,
+                dump_confidence=0.7,
+                last_update_ts=1234567890.0
+            )
+
+
+class TestVelocityMetrics:
+    """Tests for VelocityMetrics"""
+
+    def test_valid_metrics(self):
+        vel = VelocityMetrics(
+            hype_velocity=0.7,
+            pub_velocity=0.5,
+            velocity_direction="accelerating",
+            window_minutes=15,
+            source_count=3,
+            unique_assets=1
+        )
+        assert vel.hype_velocity == 0.7
+        assert vel.velocity_direction == "accelerating"
+
+
+class TestEventFlag:
+    """Tests for EventFlag"""
+
+    def test_valid_flag(self):
+        flag = EventFlag(
+            event_type="listing",
+            asset_id="BTC",
+            strength=60.0,
+            confidence=0.7,
+            first_seen_ts=1234567890.0,
+            last_seen_ts=1234567895.0,
+            source_count=2
+        )
+        assert flag.event_type == "listing"
+        assert flag.strength == 60.0
+
+
+class TestAssetSentiment:
+    """Tests for AssetSentiment"""
+
+    def test_valid_asset_sentiment(self):
+        asset = AssetSentiment(
+            asset_id="BTC",
+            fear_state=20.0,
+            greed_state=80.0,
+            sentiment_polarity=60.0,
+            emotion_profile={"joy": 0.8, "fear": 0.1, "anger": 0.05, "greed": 0.7, "sadness": 0.05, "intensity": 0.75},
+            last_update_ts=1234567890.0,
+            contributing_sources=3
+        )
+        assert asset.asset_id == "BTC"
+        assert asset.fear_state == 20.0
+
+    def test_acb_signals(self):
+        from sentiment_engine.schemas.output import MarketSentiment, SentimentOutput
+        market = MarketSentiment(
+            fear_state=25.0,
+            greed_state=75.0,
+            sentiment_index=50.0,
+            hype_velocity=65.0,
+            pub_velocity=55.0,
+            aggregate_pump_risk=75.0,
+            aggregate_dump_risk=20.0,
+            last_update_ts=1234567890.0
+        )
+        output = SentimentOutput(timestamp=1234567890.0, market=market)
+        
+        acb = output.get_acb_signals()
+        assert "market_sentiment_state" in acb
+        assert "aggregate_pump_risk" in acb
+        assert -1.0 <= acb["market_sentiment_state"] <= 1.0
+        assert 0.0 <= acb["aggregate_pump_risk"] <= 1.0
+
+    def test_book_health_veto(self):
+        from sentiment_engine.schemas.output import MarketSentiment, SentimentOutput, PumpDumpScore
+        asset = AssetSentiment(
+            asset_id="BTC",
+            fear_state=20.0,
+            greed_state=80.0,
+            sentiment_polarity=60.0,
+            pump_dump=PumpDumpScore(asset_id="BTC", pump_score=80.0, dump_score=15.0, pump_confidence=0.8, dump_confidence=0.7, last_update_ts=1234567890.0),
+            last_update_ts=1234567890.0
+        )
+        market = MarketSentiment(
+            fear_state=25.0, greed_state=75.0, sentiment_index=50.0,
+            hype_velocity=65.0, pub_velocity=55.0,
+            aggregate_pump_risk=75.0, aggregate_dump_risk=20.0,
+            last_update_ts=1234567890.0
+        )
+        output = SentimentOutput(timestamp=1234567890.0, market=market, assets={"BTC": asset})
+        
+        veto = output.get_book_health_veto(threshold=75.0)
+        assert "BTC" in veto
+        
+        veto_low = output.get_book_health_veto(threshold=85.0)
+        assert "BTC" not in veto_low
+
+
+class TestMarketSentiment:
+    """Tests for MarketSentiment"""
+
+    def test_valid_market(self):
+        market = MarketSentiment(
+            fear_state=25.0,
+            greed_state=75.0,
+            sentiment_index=50.0,
+            hype_velocity=65.0,
+            pub_velocity=55.0,
+            aggregate_pump_risk=75.0,
+            aggregate_dump_risk=20.0,
+            last_update_ts=1234567890.0
+        )
+        assert market.fear_state == 25.0
+        assert market.sentiment_index == 50.0