fix: Docker build + MCP/PyPI/ClawHub sync (v0.1.4)

- Fix #8: remove COPY data/ data/ from Dockerfile (dir doesn't exist)
- Add akshare/ccxt to requirements.txt and pyproject.toml dependencies
- Remove non-existent run_agent from py-modules
- MCP: rewrite _get_loader to use registry with fallback, add web_search tool (16→17)
- MCP: update docstrings (56→68 skills, add akshare/ccxt source docs)
- ClawHub SKILL.md: 64→68 skills, 3→5 sources, 16→17 tools, add version field
- docker-compose: remove dead fin-data volume, rename fin-→vibe- prefix
- .dockerignore: expand exclusions (tests, docs, assets, build artifacts)
- README: merge 4/10 news, update MCP 16→17, fix contributing (remove done items)
- Bump version 0.1.3→0.1.4, published to PyPI and ClawHub

Author: warren618

.dockerignore

@@ -1,28 +1,50 @@
+# Version control & CI
+.git/
+.github/
+
+# IDE & editor
+.claude/
+.vscode/
+.editorconfig
+
+# Python artifacts
 .venv/
 agent/.venv/
 __pycache__/
 *.pyc
 .pytest_cache/
 .ruff_cache/
-node_modules/
-frontend/dist/
-frontend/tsconfig.tsbuildinfo
-.env
-agent/.env
+agent/vibe_trading.egg-info/
+agent/vibe_trading_ai.egg-info/
+agent/__pycache__/
+
+# Runtime data (generated at runtime, not in repo)
+data/
 agent/runs/
 agent/sessions/
 agent/.swarm/runs/
 agent/.ui_runtime/
 agent/.tasks/
-agent/vibe_trading.egg-info/
-.git/
-.github/
-.claude/
-.vscode/
-data/*.duckdb
-data/*.duckdb.wal
-data/.duckdb_tmp/
-data/parquet/
-data/backup/
-data/minutes/
-data/*.log
+
+# Env files (mounted via docker-compose env_file)
+.env
+agent/.env
+
+# Frontend build (built inside Docker, don't copy local)
+frontend/dist/
+frontend/node_modules/
+frontend/tsconfig.tsbuildinfo
+
+# Tests & docs (not needed in production image)
+agent/tests/
+docs/
+assets/
+build/
+dist/
+
+# Project docs
+CLAUDE.md
+CONTRIBUTING.md
+*.md
+!README.md
+!LICENSE

Dockerfile

@@ -28,7 +28,6 @@ RUN pip install --no-cache-dir -r agent/requirements.txt
 # Copy project
 COPY pyproject.toml LICENSE README.md ./
 COPY agent/ agent/
-COPY data/ data/
 
 # Copy built frontend
 COPY --from=frontend-build /app/frontend/dist frontend/dist

README.md

@@ -45,7 +45,7 @@
 
 ## 📰 News
 
-- **2026-04-10** 🔧 **Performance & multi-provider**: LLM timeout 2400s→120s, all tuning params configurable via `.env`. Added 11 LLM providers (DeepSeek, Groq, Gemini, Ollama, etc.). Hardened `ml-strategy` skill template with input validation and inf/NaN sanitization.
+- **2026-04-10** 📦 **v0.1.4**: Fix Docker build ([#8](https://github.com/HKUDS/Vibe-Trading/issues/8)), add `web_search` MCP tool (17 total), `akshare`/`ccxt` in deps & MCP. 11 LLM providers (DeepSeek, Groq, Gemini, Ollama, etc.), all tuning params via `.env`. Hardened `ml-strategy` skill. Published to PyPI and ClawHub.
 - **2026-04-09** 📊 **Backtest Wave 2 — multi-asset engines**: added ChinaFutures (CFFEX/SHFE/DCE/ZCE, 50+ contracts), GlobalFutures (CME/ICE/Eurex, 30+ contracts), Forex (24 pairs, spread + swap), Options v2 (American exercise, IV smile). Statistical validation: Monte Carlo permutation test, Bootstrap Sharpe CI, Walk-Forward analysis.
 - **2026-04-08** 🔧 **Multi-market backtest** with per-market rules; **Pine Script v6 export** for TradingView. **Data source expansion**: 5 sources with auto-fallback, `web_search` tool, skill categorization (7 categories).
 - **2026-04-01** 🚀 **v0.1.0** — Initial release: ReAct agent, 64 skills, 29 swarm presets, cross-market backtest, CLI + Web UI + MCP server.
@@ -227,7 +227,7 @@ vibe-trading-mcp               # start MCP server (stdio)
 git clone https://github.com/HKUDS/Vibe-Trading.git
 cd Vibe-Trading
 cp agent/.env.example agent/.env
-# Edit agent/.env — set OPENAI_API_KEY (required)
+# Edit agent/.env — uncomment your LLM provider and set API key
 docker compose up --build
 ```
 
@@ -245,7 +245,7 @@ source .venv/bin/activate          # Linux / macOS
 # .venv\Scripts\Activate.ps1       # Windows PowerShell
 
 pip install -e .
-cp agent/.env.example agent/.env   # Edit — set OPENAI_API_KEY
+cp agent/.env.example agent/.env   # Edit — set your LLM provider API key
 vibe-trading                       # Launch interactive TUI
 ```
 
@@ -390,7 +390,7 @@ Interactive docs: `http://localhost:8899/docs`
 
 ## 🔌 MCP Plugin
 
-Vibe-Trading exposes 16 MCP tools for any MCP-compatible client. Runs as a stdio subprocess — no server setup needed. **15 of 16 tools work with zero API keys** (HK/US/crypto). Only `run_swarm` needs an LLM key.
+Vibe-Trading exposes 17 MCP tools for any MCP-compatible client. Runs as a stdio subprocess — no server setup needed. **16 of 17 tools work with zero API keys** (HK/US/crypto). Only `run_swarm` needs an LLM key.
 
 <details>
 <summary><b>Claude Desktop</b></summary>
@@ -432,7 +432,7 @@ vibe-trading-mcp --transport sse  # SSE for web clients
 
 </details>
 
-**MCP tools exposed (16):** `list_skills`, `load_skill`, `backtest`, `factor_analysis`, `analyze_options`, `pattern_recognition`, `get_market_data`, `read_url`, `read_document`, `read_file`, `write_file`, `list_swarm_presets`, `run_swarm`, `get_swarm_status`, `get_run_result`, `list_runs`.
+**MCP tools exposed (17):** `list_skills`, `load_skill`, `backtest`, `factor_analysis`, `analyze_options`, `pattern_recognition`, `get_market_data`, `web_search`, `read_url`, `read_document`, `read_file`, `write_file`, `list_swarm_presets`, `run_swarm`, `get_swarm_status`, `get_run_result`, `list_runs`.
 
 <details>
 <summary><b>Install from ClawHub (one command)</b></summary>
@@ -490,7 +490,7 @@ Vibe-Trading/
 ├── agent/                          # Backend (Python)
 │   ├── cli.py                      # CLI entrypoint — interactive TUI + subcommands
 │   ├── api_server.py               # FastAPI server — runs, sessions, upload, swarm, SSE
-│   ├── mcp_server.py               # MCP server — 16 tools for OpenClaw / Claude Desktop
+│   ├── mcp_server.py               # MCP server — 17 tools for OpenClaw / Claude Desktop
 │   │
 │   ├── src/
 │   │   ├── agent/                  # ReAct agent core
@@ -518,7 +518,7 @@ Vibe-Trading/
 │   │   └── providers/              # LLM provider abstraction
 │   │
 │   ├── backtest/                   # Backtest engines
-│   │   ├── engines/                #   daily_portfolio + options_portfolio
+│   │   ├── engines/                #   7 engines: china_a, global_equity, crypto, china_futures, global_futures, forex + options_portfolio
 │   │   ├── loaders/                #   5 sources: tushare, okx, yfinance, akshare, ccxt
 │   │   │   ├── base.py             #   DataLoader Protocol
 │   │   │   └── registry.py         #   Registry + auto-fallback chains
@@ -579,9 +579,7 @@ Areas we'd love help with:
 
 | Area | Difficulty | Description |
 |------|:----------:|-------------|
-| Intraday backtest engine | Hard | Sub-daily (1m/5m/1H) bar execution with proper session handling |
 | Options vol surface & Greeks viz | Hard | 3D implied-vol surface, delta/gamma/vega charts in frontend |
-| Monte Carlo & stress testing | Hard | Scenario simulation, regime-switching, tail-risk analysis |
 | Portfolio optimizer constraints | Medium | Leverage limits, sector caps, turnover penalties |
 | Correlation heatmap dashboard | Medium | Cross-asset correlation matrix with time-window slider |
 | New data source loader | Medium | Implement `DataLoader` Protocol for a new exchange/vendor |

agent/SKILL.md

@@ -1,6 +1,7 @@
 ---
 name: vibe-trading
-description: Professional finance research toolkit — backtesting, factor analysis, options pricing, 64 finance skills, and 29 multi-agent swarm teams across 3 markets (A-shares, crypto, HK/US equities).
+version: 0.1.4
+description: Professional finance research toolkit — backtesting (6 engines), factor analysis, options pricing, 68 finance skills, and 29 multi-agent swarm teams across 5 data sources (tushare, yfinance, okx, akshare, ccxt).
 dependencies:
   python: ">=3.11"
   pip:
@@ -10,7 +11,7 @@ env:
     description: "Tushare API token for China A-share data (optional — HK/US/crypto work without any key)"
     required: false
   - name: OPENAI_API_KEY
-    description: "OpenAI-compatible API key — only needed for run_swarm (multi-agent teams). All other 15 tools work without it."
+    description: "OpenAI-compatible API key — only needed for run_swarm (multi-agent teams). All other 16 tools work without it."
     required: false
   - name: LANGCHAIN_MODEL_NAME
     description: "LLM model name for run_swarm (e.g. deepseek/deepseek-v3.2). Only needed if using run_swarm."
@@ -22,7 +23,7 @@ mcp:
 
 # Vibe-Trading
 
-Professional finance research toolkit with AI-powered backtesting, multi-agent teams, and 64 specialized skills.
+Professional finance research toolkit with AI-powered backtesting (6 engines), multi-agent teams, and 68 specialized skills.
 
 ## Setup
 
@@ -52,7 +53,7 @@ Add to your agent's MCP config:
 
 ### API Key Requirements
 
-**15 of 16 MCP tools work with zero API keys.** After `pip install`, backtesting, market data, factor analysis, options pricing, chart patterns, and all 64 skills are ready to use for HK/US equities and crypto.
+**16 of 17 MCP tools work with zero API keys.** After `pip install`, backtesting, market data, factor analysis, options pricing, chart patterns, web search, and all 68 skills are ready to use for HK/US equities and crypto.
 
 | Feature | Key needed | When |
 |---------|-----------|------|
@@ -63,10 +64,11 @@ Add to your agent's MCP config:
 ## What You Can Do
 
 ### Backtesting
-Create and run quantitative strategies across 3 markets:
+Create and run quantitative strategies across 6 engines (ChinaA, GlobalEquity, Crypto, ChinaFutures, GlobalFutures, Forex + options) with 5 data sources:
 - **HK/US equities** via yfinance (free, no API key)
-- **Cryptocurrency** via OKX (free, no API key)
-- **China A-shares** via Tushare (requires TUSHARE_TOKEN)
+- **Cryptocurrency** via OKX or CCXT/100+ exchanges (free, no API key)
+- **China A-shares** via Tushare (token) or AKShare (free fallback)
+- **Futures, forex, macro** via AKShare (free, no API key)
 
 Example workflow:
 1. Use `list_skills()` to discover strategy patterns
@@ -87,7 +89,7 @@ Example workflow:
 
 Use `list_swarm_presets()` to see all teams, then `run_swarm()` to execute.
 
-### Finance Skills (64)
+### Finance Skills (68)
 Comprehensive knowledge base covering:
 - Technical analysis (candlestick, Elliott wave, Ichimoku, SMC)
 - Quantitative methods (factor research, ML strategy, pair trading)
@@ -99,17 +101,18 @@ Comprehensive knowledge base covering:
 
 Use `load_skill(name)` to access full methodology docs with code templates.
 
-## Available MCP Tools (16)
+## Available MCP Tools (17)
 
 | Tool | Description | API Key |
 |------|-------------|---------|
-| `list_skills` | List all 64 finance skills | None |
+| `list_skills` | List all 68 finance skills | None |
 | `load_skill` | Load full skill documentation | None |
 | `backtest` | Run vectorized backtest engine | None* |
 | `factor_analysis` | IC/IR analysis + layered backtest | None* |
 | `analyze_options` | Black-Scholes price + Greeks | None |
 | `pattern_recognition` | Detect chart patterns (H&S, double top, etc.) | None |
-| `get_market_data` | Fetch OHLCV data across 3 markets (auto-detect source) | None* |
+| `get_market_data` | Fetch OHLCV data across 5 sources (auto-detect + fallback) | None* |
+| `web_search` | Search the web via DuckDuckGo | None |
 | `read_url` | Fetch web page as Markdown | None |
 | `read_document` | Extract text from PDF (with OCR) | None |
 | `write_file` | Write files (config, strategy code) | None |
@@ -128,7 +131,7 @@ Use `load_skill(name)` to access full methodology docs with code templates.
 pip install vibe-trading-ai
 ```
 
-That's it — no API keys needed for HK/US/crypto markets. Start using `backtest`, `get_market_data`, `analyze_options`, and all 64 skills immediately.
+That's it — no API keys needed for HK/US/crypto markets. Start using `backtest`, `get_market_data`, `analyze_options`, `web_search`, and all 68 skills immediately.
 
 ## Examples
 

agent/mcp_server.py

@@ -1,8 +1,8 @@
 #!/usr/bin/env python3
-"""Vibe-Trading MCP Server — expose 16 finance research tools to any MCP client.
+"""Vibe-Trading MCP Server — expose 17 finance research tools to any MCP client.
 
 Works with OpenClaw, Claude Desktop, Cursor, and any MCP-compatible client.
-Zero API key required for HK/US/crypto markets (yfinance + OKX are free).
+Zero API key required for HK/US/crypto markets (yfinance, OKX, AKShare are free).
 
 Usage:
     python mcp_server.py                    # stdio transport (default)
@@ -75,7 +75,7 @@ def _get_registry():
 def list_skills() -> str:
     """List all available finance skills with names and descriptions.
 
-    Returns a JSON array of {name, description} for all 56 skills.
+    Returns a JSON array of {name, description} for all 68 skills.
     Use load_skill(name) to get the full documentation for any skill.
     """
     loader = _get_skills_loader()
@@ -117,7 +117,9 @@ def backtest(run_dir: str) -> str:
     - "yfinance": HK/US equities (free, no API key needed)
     - "okx": cryptocurrency (free, no API key needed)
     - "tushare": China A-shares (requires TUSHARE_TOKEN env var)
-    - "auto": auto-detect based on symbol format
+    - "akshare": A-shares, US, HK, futures, forex (free, no API key)
+    - "ccxt": crypto from 100+ exchanges (free, no API key)
+    - "auto": auto-detect based on symbol format (with fallback)
 
     Returns metrics (Sharpe, return, drawdown, etc.) and artifact paths.
 
@@ -246,6 +248,27 @@ def read_document(file_path: str) -> str:
     return registry.execute("read_document", {"file_path": file_path})
 
 
+# ---------------------------------------------------------------------------
+# Web search tool
+# ---------------------------------------------------------------------------
+
+@mcp.tool
+def web_search(query: str, max_results: int = 5) -> str:
+    """Search the web via DuckDuckGo and return top results.
+
+    Returns titles, URLs, and snippets. Use read_url() to fetch full content
+    from any result URL. Free, no API key required.
+
+    Args:
+        query: Search query string.
+        max_results: Maximum results to return (default 5, max 10).
+    """
+    registry = _get_registry()
+    return registry.execute("web_search", {
+        "query": query, "max_results": min(max_results, 10),
+    })
+
+
 # ---------------------------------------------------------------------------
 # File I/O tools (sandboxed to workspace)
 # ---------------------------------------------------------------------------
@@ -354,6 +377,7 @@ def run_swarm(preset_name: str, variables: dict[str, str]) -> str:
     (re.compile(r"^[A-Z]+\.US$", re.I), "yfinance"),
     (re.compile(r"^\d{3,5}\.HK$", re.I), "yfinance"),
     (re.compile(r"^[A-Z]+-USDT$", re.I), "okx"),
+    (re.compile(r"^[A-Z]+/USDT$", re.I), "ccxt"),
 ]
 
 
@@ -365,13 +389,9 @@ def _detect_source(code: str) -> str:
 
 
 def _get_loader(source: str):
-    if source == "okx":
-        from backtest.loaders.okx import DataLoader
-    elif source == "yfinance":
-        from backtest.loaders.yfinance_loader import DataLoader
-    else:
-        from backtest.loaders.tushare import DataLoader
-    return DataLoader
+    """Get loader class via registry with fallback support."""
+    from backtest.loaders.registry import get_loader_cls_with_fallback
+    return get_loader_cls_with_fallback(source)
 
 
 @mcp.tool
@@ -388,13 +408,15 @@ def get_market_data(
     - "yfinance": HK/US equities (free, e.g. AAPL.US, 700.HK)
     - "okx": cryptocurrency (free, e.g. BTC-USDT, ETH-USDT)
     - "tushare": China A-shares (requires TUSHARE_TOKEN, e.g. 000001.SZ)
-    - "auto": auto-detect based on symbol format (supports mixed markets)
+    - "akshare": A-shares, US, HK, futures, forex (free, e.g. 000001.SZ, AAPL.US)
+    - "ccxt": crypto from 100+ exchanges (free, e.g. BTC/USDT)
+    - "auto": auto-detect based on symbol format (with fallback)
 
     Args:
         codes: List of symbols (e.g. ["AAPL.US", "BTC-USDT", "000001.SZ"]).
         start_date: Start date (YYYY-MM-DD).
         end_date: End date (YYYY-MM-DD).
-        source: Data source ("auto", "yfinance", "okx", "tushare").
+        source: Data source ("auto", "yfinance", "okx", "tushare", "akshare", "ccxt").
         interval: Bar size (1m/5m/15m/30m/1H/4H/1D, default "1D").
     """
     results = {}

agent/requirements.txt

@@ -26,6 +26,8 @@ pyharmonics>=1.5.0
 tushare>=1.2.89
 requests>=2.31.0
 yfinance>=0.2.30
+akshare>=1.12.0
+ccxt>=4.0.0
 
 # REST API & SSE
 fastapi>=0.104.0

docker-compose.yml

@@ -6,12 +6,10 @@ services:
     env_file:
       - agent/.env
     volumes:
-      - fin-data:/app/data
-      - fin-runs:/app/agent/runs
-      - fin-sessions:/app/agent/sessions
+      - vibe-runs:/app/agent/runs
+      - vibe-sessions:/app/agent/sessions
     restart: unless-stopped
 
 volumes:
-  fin-data:
-  fin-runs:
-  fin-sessions:
+  vibe-runs:
+  vibe-sessions:

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "vibe-trading-ai"
-version = "0.1.3"
+version = "0.1.4"
 description = "Natural-language finance research AI agent with backtesting"
 requires-python = ">=3.11"
 license = "MIT"
@@ -36,6 +36,8 @@ dependencies = [
     "tushare>=1.2.89",
     "requests>=2.31.0",
     "yfinance>=0.2.30",
+    "akshare>=1.12.0",
+    "ccxt>=4.0.0",
     "fastapi>=0.104.0",
     "uvicorn[standard]>=0.24.0",
     "pydantic>=2.0.0",
@@ -55,7 +57,7 @@ vibe-trading-mcp = "mcp_server:main"
 
 [tool.setuptools]
 package-dir = {"" = "agent"}
-py-modules = ["cli", "run_agent", "api_server", "mcp_server"]
+py-modules = ["cli", "api_server", "mcp_server"]
 
 [tool.setuptools.packages.find]
 where = ["agent"]