@vizzor/cli 0.14.6 → 0.15.0

package/README.md

@@ -72,6 +72,7 @@ That's it. Vizzor launches a guided setup wizard that walks you through:
 - Choosing your AI provider (Claude, GPT-4, Gemini, or local Ollama)
 - Setting up API keys
 - Picking your default chain
+- Optionally installing the ChronoVisor ML engine on first run
 - Learning the first commands
 
 ### Start predicting
@@ -88,7 +89,8 @@ That's it. Vizzor launches a guided setup wizard that walks you through:
 ### Better prediction accuracy
 
 After setup, follow these tips for the best results:
-- Run `/cosmos on` to enable full data pipeline
+- Enable the ChronoVisor engine during setup, or run `vizzor chronovisor setup` later
+- Run `/cosmos on` for stricter tracked-only qualification and fewer low-edge setups
 - For intraday: focus on `BTC`, `ETH`, and `SOL` with `2h`, `3h`, `4h`, `6h` horizons
 - For scalping: focus on `BTC` and `ETH` with exact short horizons like `10m`, `20m`, `45m`
 - For long-range: ask for `7d`, `30d`, `90d`, or `1y` scenario ranges
@@ -457,6 +459,12 @@ WS   /ws                              # WebSocket real-time push
 
 The ChronoVisor engine is an optional Python-based prediction accelerator with 16 trained models that enhances Vizzor's predictions with ML. When unavailable, Vizzor falls back to its rule-based heuristics automatically — no setup required to start using Vizzor.
 
+If your tracked setups keep getting skipped, check whether ChronoVisor is actually enabled and healthy:
+
+```bash
+vizzor chronovisor status
+```
+
 ### Quick setup
 
 ```bash

package/chronovisor-engine/Dockerfile

@@ -0,0 +1,12 @@
+FROM python:3.11-slim
+
+WORKDIR /app
+
+COPY pyproject.toml .
+COPY src/ src/
+
+RUN pip install --no-cache-dir .
+
+EXPOSE 7200
+
+CMD ["uvicorn", "src.server:app", "--host", "0.0.0.0", "--port", "7200"]

package/chronovisor-engine/models/regime_detector/metrics_1773536830.json

@@ -0,0 +1,36 @@
+{
+  "accuracy": 0.22,
+  "per_class": {
+    "trending_bull": {
+      "precision": 0.14285714285714285,
+      "recall": 0.09090909090909091,
+      "f1-score": 0.1111111111111111,
+      "support": 33.0
+    },
+    "trending_bear": {
+      "precision": 0.208955223880597,
+      "recall": 0.45161290322580644,
+      "f1-score": 0.2857142857142857,
+      "support": 31.0
+    },
+    "ranging": {
+      "precision": 0.20689655172413793,
+      "recall": 0.2222222222222222,
+      "f1-score": 0.21428571428571427,
+      "support": 27.0
+    },
+    "volatile": {
+      "precision": 0.2857142857142857,
+      "recall": 0.1875,
+      "f1-score": 0.22641509433962265,
+      "support": 32.0
+    },
+    "capitulation": {
+      "precision": 0.3333333333333333,
+      "recall": 0.14814814814814814,
+      "f1-score": 0.20512820512820512,
+      "support": 27.0
+    }
+  },
+  "test_samples": 150
+}

package/chronovisor-engine/models/rug_detector/metrics_1773536830.json

@@ -0,0 +1,7 @@
+{
+  "accuracy": 0.96,
+  "precision": 0.9285714285714286,
+  "recall": 0.8666666666666667,
+  "f1": 0.896551724137931,
+  "test_samples": 150
+}

package/chronovisor-engine/models/sentiment_nlp/metrics_1773536831.json

@@ -0,0 +1,4 @@
+{
+  "accuracy": 0.37333333333333335,
+  "test_samples": 75
+}

package/chronovisor-engine/models/trend_scorer/metrics_1773536830.json

@@ -0,0 +1,5 @@
+{
+  "r2": 0.9008962744572128,
+  "mae": 9.576466093118714,
+  "test_samples": 150
+}

package/chronovisor-engine/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "vizzor-ml-sidecar"
-version = "0.14.5"
+version = "0.15.0"
 description = "ML sidecar for Vizzor — LSTM, RF, Isolation Forest, Rug Detection, Wallet Classification, Sentiment NLP, Trend Scoring, TA Interpretation, Regime Detection, Strategy Bandit, Project Risk, Portfolio Optimization, Intent Classification"
 requires-python = ">=3.11"
 dependencies = [

package/chronovisor-engine/src/server.py

@@ -664,7 +664,7 @@ async def lifespan(_app: FastAPI):
 
 app = FastAPI(
     title="Vizzor ML Sidecar",
-    version="0.14.5",
+    version="0.15.0",
     lifespan=lifespan,
 )
 
@@ -1509,6 +1509,7 @@ async def catalog_roadmap():
 @app.get("/health")
 async def health():
     return {
+        "version": app.version,
         "models": [
             {
                 "name": "lstm-predictor",