确认PokieTicker新闻库数据源

runs/reload_demo/BOOTSTRAP.md

@@ -0,0 +1,18 @@
+---
+tickers:
+  - NVDA
+  - AMD
+initial_cash: 250000
+margin_requirement: 0.5
+enable_memory: false
+max_comm_cycles: 1
+agent_overrides:
+  risk_manager:
+    active_tool_groups:
+      - risk_ops
+---
+
+# Bootstrap
+
+Prefer semiconductor names in this run.
+Keep decisions terse and explicitly mention concentration risk.

runs/reload_demo/agents/fundamentals_analyst/POLICY.md

@@ -0,0 +1,5 @@
+# Policy
+
+Optional run-scoped constraints, limits, or strategy policy.
+
+State a clear signal, confidence, and the conditions that would invalidate the thesis.

runs/reload_demo/agents/fundamentals_analyst/ROLE.md

@@ -0,0 +1,11 @@
+# Role
+
+Optional run-scoped role override.
+
+作为基本面分析师，你专注于：
+- 公司财务健康状况和盈利能力
+- 商业模式可持续性和竞争优势
+- 管理层质量和公司治理
+- 行业地位和市场份额
+- 长期投资价值评估
+你倾向于选择能够深入了解公司内在价值的工具，更偏好基本面和估值类工具。

runs/reload_demo/agents/fundamentals_analyst/STYLE.md

@@ -0,0 +1,9 @@
+# Style
+
+Optional run-scoped communication or reasoning style.
+
+- 公司财务健康状况和盈利能力
+- 商业模式可持续性和竞争优势
+- 管理层质量和公司治理
+- 行业地位和市场份额
+- 长期投资价值评估

runs/reload_demo/agents/portfolio_manager/POLICY.md

@@ -0,0 +1,5 @@
+# Policy
+
+Optional run-scoped constraints, limits, or strategy policy.
+
+Respect cash, margin, and portfolio concentration constraints before recording decisions.

runs/reload_demo/agents/portfolio_manager/ROLE.md

@@ -0,0 +1,5 @@
+# Role
+
+Optional run-scoped role override.
+
+Synthesize analyst and risk inputs into explicit portfolio decisions.

runs/reload_demo/agents/portfolio_manager/STYLE.md

@@ -0,0 +1,5 @@
+# Style
+
+Optional run-scoped communication or reasoning style.
+
+Be concise, capital-aware, and explicit about sizing rationale.

runs/reload_demo/agents/risk_manager/POLICY.md

@@ -0,0 +1,5 @@
+# Policy
+
+Optional run-scoped constraints, limits, or strategy policy.
+
+Use available risk tools before issuing the final risk memo.

runs/reload_demo/agents/risk_manager/ROLE.md

@@ -0,0 +1,5 @@
+# Role
+
+Optional run-scoped role override.
+
+Quantify concentration, leverage, liquidity, and volatility risk before trade execution.

runs/reload_demo/agents/risk_manager/STYLE.md

@@ -0,0 +1,6 @@
+# Style
+
+Optional run-scoped communication or reasoning style.
+
+Prioritize the highest-severity semiconductor risk first.
+Always state one concrete position limit and one liquidation trigger.

runs/reload_demo/agents/sentiment_analyst/POLICY.md

@@ -0,0 +1,5 @@
+# Policy
+
+Optional run-scoped constraints, limits, or strategy policy.
+
+State a clear signal, confidence, and the conditions that would invalidate the thesis.

runs/reload_demo/agents/sentiment_analyst/ROLE.md

@@ -0,0 +1,11 @@
+# Role
+
+Optional run-scoped role override.
+
+作为情绪分析师，你专注于：
+- 市场参与者情绪变化
+- 新闻舆情和媒体影响
+- 内部人交易行为
+- 投资者恐慌和贪婪情绪
+- 市场预期和心理因素
+你倾向于选择能够反映市场情绪和投资者行为的工具，更偏好情绪和行为类工具。

runs/reload_demo/agents/sentiment_analyst/STYLE.md

@@ -0,0 +1,9 @@
+# Style
+
+Optional run-scoped communication or reasoning style.
+
+- 市场参与者情绪变化
+- 新闻舆情和媒体影响
+- 内部人交易行为
+- 投资者恐慌和贪婪情绪
+- 市场预期和心理因素

runs/reload_demo/agents/technical_analyst/POLICY.md

@@ -0,0 +1,5 @@
+# Policy
+
+Optional run-scoped constraints, limits, or strategy policy.
+
+State a clear signal, confidence, and the conditions that would invalidate the thesis.

runs/reload_demo/agents/technical_analyst/ROLE.md

@@ -0,0 +1,11 @@
+# Role
+
+Optional run-scoped role override.
+
+作为技术分析师，你专注于：
+- 价格趋势和图表形态
+- 技术指标和交易信号
+- 市场情绪和资金流向
+- 支撑/阻力位和关键价格点
+- 中短期交易机会
+你倾向于选择能够捕捉价格动态和市场趋势的工具，更偏好技术分析类工具。

runs/reload_demo/agents/technical_analyst/STYLE.md

@@ -0,0 +1,9 @@
+# Style
+
+Optional run-scoped communication or reasoning style.
+
+- 价格趋势和图表形态
+- 技术指标和交易信号
+- 市场情绪和资金流向
+- 支撑/阻力位和关键价格点
+- 中短期交易机会

runs/reload_demo/agents/valuation_analyst/POLICY.md

@@ -0,0 +1,5 @@
+# Policy
+
+Optional run-scoped constraints, limits, or strategy policy.
+
+State a clear signal, confidence, and the conditions that would invalidate the thesis.

runs/reload_demo/agents/valuation_analyst/ROLE.md

@@ -0,0 +1,11 @@
+# Role
+
+Optional run-scoped role override.
+
+作为估值分析师，你专注于：
+- 公司内在价值计算
+- 不同估值方法的比较
+- 估值模型假设和敏感性分析
+- 相对估值和绝对估值
+- 投资安全边际评估
+你倾向于选择能够准确计算公司价值的工具，更偏好估值模型和基本面工具。

runs/reload_demo/agents/valuation_analyst/STYLE.md

@@ -0,0 +1,9 @@
+# Style
+
+Optional run-scoped communication or reasoning style.
+
+- 公司内在价值计算
+- 不同估值方法的比较
+- 估值模型假设和敏感性分析
+- 相对估值和绝对估值
+- 投资安全边际评估

runs/reload_demo/skills/activation.yaml

@@ -0,0 +1,8 @@
+global_enabled_skills: []
+global_disabled_skills: []
+agent_enabled_skills:
+  risk_manager:
+    - technical_review
+  portfolio_manager:
+    - risk_review
+agent_disabled_skills: {}

runs/reload_demo/skills/active/fundamental_review/SKILL.md

@@ -0,0 +1,21 @@
+---
+name: fundamental_review
+description: Review a company from a fundamentals-first perspective before issuing a trading signal.
+---
+
+# Fundamental Review
+
+Use this skill when the task requires judging business quality, balance-sheet strength, profitability, or long-term earnings durability.
+
+## Workflow
+
+1. Check profitability, growth, financial health, and efficiency before forming a conclusion.
+2. Separate durable business quality from short-term noise.
+3. State what would invalidate the thesis.
+4. End with a clear signal, confidence, and the main drivers behind that signal.
+
+## Guardrails
+
+- Do not rely on one metric in isolation.
+- Call out missing data explicitly.
+- Prefer conservative conclusions when financial quality is mixed.

runs/reload_demo/skills/active/portfolio_decisioning/SKILL.md

@@ -0,0 +1,21 @@
+---
+name: portfolio_decisioning
+description: Synthesize analyst inputs and risk feedback into explicit portfolio decisions.
+---
+
+# Portfolio Decisioning
+
+Use this skill when you are responsible for converting team analysis into final trades.
+
+## Workflow
+
+1. Read analyst conclusions and risk warnings before acting.
+2. Evaluate the current portfolio, cash, and margin constraints.
+3. Record one explicit decision per ticker using the decision tool.
+4. Summarize the portfolio-level rationale after all decisions are recorded.
+
+## Guardrails
+
+- Position sizing must respect capital and margin limits.
+- Prefer smaller size when analyst conviction and risk signals disagree.
+- Do not leave a ticker undecided when the task expects a full slate of decisions.

runs/reload_demo/skills/active/risk_review/SKILL.md

@@ -0,0 +1,21 @@
+---
+name: risk_review
+description: Assess portfolio and market risks before final position sizing and execution.
+---
+
+# Risk Review
+
+Use this skill when you must identify concentration, volatility, leverage, and scenario risks.
+
+## Workflow
+
+1. Review the proposed exposure by ticker and theme.
+2. Identify concentration, volatility, liquidity, and leverage concerns.
+3. Rank warnings by severity.
+4. Translate risk findings into concrete limits or cautions for the portfolio manager.
+
+## Guardrails
+
+- Focus on actionable risk controls.
+- Quantify limits when the available data supports it.
+- Distinguish fatal blockers from manageable risks.

runs/reload_demo/skills/active/sentiment_review/SKILL.md

@@ -0,0 +1,21 @@
+---
+name: sentiment_review
+description: Analyze news flow, market psychology, and insider behavior for catalyst-driven signals.
+---
+
+# Sentiment Review
+
+Use this skill when the task depends on recent catalysts, news tone, or behavioral market signals.
+
+## Workflow
+
+1. Review recent news and identify the dominant narrative.
+2. Check insider activity for confirming or conflicting signals.
+3. Separate durable sentiment shifts from transient noise.
+4. Explain how sentiment changes the near-term trade outlook.
+
+## Guardrails
+
+- Do not confuse attention with conviction.
+- Highlight when sentiment is strong but unsupported by fundamentals.
+- Be explicit about catalyst timing risk.

runs/reload_demo/skills/active/technical_review/SKILL.md

@@ -0,0 +1,21 @@
+---
+name: technical_review
+description: Evaluate price action, momentum, and volatility to judge timing and market regime.
+---
+
+# Technical Review
+
+Use this skill when the task is sensitive to entry timing, trend quality, or short-term market structure.
+
+## Workflow
+
+1. Assess trend direction and strength.
+2. Check momentum and mean-reversion conditions.
+3. Review volatility before making aggressive recommendations.
+4. Convert the setup into a trading view with explicit risk awareness.
+
+## Guardrails
+
+- Distinguish trend continuation from overshoot.
+- Avoid strong conviction when signals conflict.
+- Treat volatility as a sizing input, not only a directional input.

runs/reload_demo/skills/active/valuation_review/SKILL.md

@@ -0,0 +1,21 @@
+---
+name: valuation_review
+description: Estimate fair value and margin of safety using multiple valuation lenses.
+---
+
+# Valuation Review
+
+Use this skill when the task requires determining whether a stock is cheap, expensive, or fairly priced.
+
+## Workflow
+
+1. Use more than one valuation method when possible.
+2. Compare intrinsic value estimates with current market pricing.
+3. Explain the key assumptions behind the valuation view.
+4. State the margin of safety and what could compress or expand it.
+
+## Guardrails
+
+- Treat valuation as a range, not a single precise number.
+- Call out assumption sensitivity.
+- Avoid high-confidence calls when inputs are sparse or unstable.

runs/reload_demo/state/server_state.json

@@ -0,0 +1,206 @@
+{
+  "status": "running",
+  "current_date": "2026-03-16",
+  "portfolio": {
+    "total_value": 250000.0,
+    "cash": 250000.0,
+    "pnl_percent": 0.0,
+    "equity": [],
+    "baseline": [],
+    "baseline_vw": [],
+    "momentum": [],
+    "strategies": [],
+    "equity_return": [],
+    "baseline_return": [],
+    "baseline_vw_return": [],
+    "momentum_return": []
+  },
+  "holdings": [],
+  "trades": [],
+  "stats": {
+    "totalAssetValue": 250000.0,
+    "totalReturn": 0.0,
+    "cashPosition": 250000.0,
+    "tickerWeights": {},
+    "totalTrades": 0,
+    "winRate": 0.0,
+    "bullBear": {
+      "bull": {
+        "n": 0,
+        "win": 0
+      },
+      "bear": {
+        "n": 0,
+        "win": 0
+      }
+    }
+  },
+  "leaderboard": [
+    {
+      "agentId": "portfolio_manager",
+      "name": "投资经理",
+      "role": "投资经理",
+      "avatar": "pm",
+      "rank": null,
+      "winRate": null,
+      "bull": {
+        "n": 0,
+        "win": 0,
+        "unknown": 0
+      },
+      "bear": {
+        "n": 0,
+        "win": 0,
+        "unknown": 0
+      },
+      "logs": [],
+      "signals": [],
+      "modelName": "deepseek-v3.2",
+      "modelProvider": "DASHSCOPE"
+    },
+    {
+      "agentId": "risk_manager",
+      "name": "风控经理",
+      "role": "风控经理",
+      "avatar": "risk",
+      "rank": null,
+      "winRate": null,
+      "bull": {
+        "n": 0,
+        "win": 0,
+        "unknown": 0
+      },
+      "bear": {
+        "n": 0,
+        "win": 0,
+        "unknown": 0
+      },
+      "logs": [],
+      "signals": [],
+      "modelName": "deepseek-v3.2",
+      "modelProvider": "DASHSCOPE"
+    },
+    {
+      "agentId": "sentiment_analyst",
+      "name": "情绪分析师",
+      "role": "情绪分析师",
+      "avatar": "sentiment",
+      "rank": 0,
+      "winRate": null,
+      "bull": {
+        "n": 0,
+        "win": 0,
+        "unknown": 0
+      },
+      "bear": {
+        "n": 0,
+        "win": 0,
+        "unknown": 0
+      },
+      "logs": [],
+      "signals": [],
+      "modelName": "deepseek-v3.2",
+      "modelProvider": "DASHSCOPE"
+    },
+    {
+      "agentId": "technical_analyst",
+      "name": "技术分析师",
+      "role": "技术分析师",
+      "avatar": "technical",
+      "rank": 0,
+      "winRate": null,
+      "bull": {
+        "n": 0,
+        "win": 0,
+        "unknown": 0
+      },
+      "bear": {
+        "n": 0,
+        "win": 0,
+        "unknown": 0
+      },
+      "logs": [],
+      "signals": [],
+      "modelName": "deepseek-v3.2",
+      "modelProvider": "DASHSCOPE"
+    },
+    {
+      "agentId": "fundamentals_analyst",
+      "name": "基本面分析师",
+      "role": "基本面分析师",
+      "avatar": "fundamentals",
+      "rank": 0,
+      "winRate": null,
+      "bull": {
+        "n": 0,
+        "win": 0,
+        "unknown": 0
+      },
+      "bear": {
+        "n": 0,
+        "win": 0,
+        "unknown": 0
+      },
+      "logs": [],
+      "signals": [],
+      "modelName": "deepseek-v3.2",
+      "modelProvider": "DASHSCOPE"
+    },
+    {
+      "agentId": "valuation_analyst",
+      "name": "估值分析师",
+      "role": "估值分析师",
+      "avatar": "valuation",
+      "rank": 0,
+      "winRate": null,
+      "bull": {
+        "n": 0,
+        "win": 0,
+        "unknown": 0
+      },
+      "bear": {
+        "n": 0,
+        "win": 0,
+        "unknown": 0
+      },
+      "logs": [],
+      "signals": [],
+      "modelName": "deepseek-v3.2",
+      "modelProvider": "DASHSCOPE"
+    }
+  ],
+  "realtime_prices": {},
+  "system_started": "2026-03-16T00:38:27.957651",
+  "feed_history": [
+    {
+      "type": "system",
+      "content": "Runtime assets reloaded.",
+      "timestamp": "2026-03-16"
+    },
+    {
+      "type": "day_start",
+      "date": "2026-03-16",
+      "progress": 0.0,
+      "timestamp": "2026-03-16"
+    }
+  ],
+  "last_day_history": [],
+  "trading_days_total": 0,
+  "trading_days_completed": 0,
+  "server_mode": "live",
+  "is_backtest": false,
+  "is_mock_mode": true,
+  "data_sources": {
+    "preferred": [
+      "yfinance",
+      "financial_datasets",
+      "finnhub",
+      "local_csv"
+    ],
+    "last_success": {
+      "market_cap": "financial_datasets",
+      "financial_metrics": "yfinance"
+    }
+  },
+  "last_saved": "2026-03-16T00:38:59.051101"
+}

runs/reload_demo/team_dashboard/holdings.json

@@ -0,0 +1 @@
+[]

runs/reload_demo/team_dashboard/leaderboard.json

@@ -0,0 +1,134 @@
+[
+  {
+    "agentId": "portfolio_manager",
+    "name": "投资经理",
+    "role": "投资经理",
+    "avatar": "pm",
+    "rank": null,
+    "winRate": null,
+    "bull": {
+      "n": 0,
+      "win": 0,
+      "unknown": 0
+    },
+    "bear": {
+      "n": 0,
+      "win": 0,
+      "unknown": 0
+    },
+    "logs": [],
+    "signals": [],
+    "modelName": "deepseek-v3.2",
+    "modelProvider": "DASHSCOPE"
+  },
+  {
+    "agentId": "risk_manager",
+    "name": "风控经理",
+    "role": "风控经理",
+    "avatar": "risk",
+    "rank": null,
+    "winRate": null,
+    "bull": {
+      "n": 0,
+      "win": 0,
+      "unknown": 0
+    },
+    "bear": {
+      "n": 0,
+      "win": 0,
+      "unknown": 0
+    },
+    "logs": [],
+    "signals": [],
+    "modelName": "deepseek-v3.2",
+    "modelProvider": "DASHSCOPE"
+  },
+  {
+    "agentId": "sentiment_analyst",
+    "name": "情绪分析师",
+    "role": "情绪分析师",
+    "avatar": "sentiment",
+    "rank": 0,
+    "winRate": null,
+    "bull": {
+      "n": 0,
+      "win": 0,
+      "unknown": 0
+    },
+    "bear": {
+      "n": 0,
+      "win": 0,
+      "unknown": 0
+    },
+    "logs": [],
+    "signals": [],
+    "modelName": "deepseek-v3.2",
+    "modelProvider": "DASHSCOPE"
+  },
+  {
+    "agentId": "technical_analyst",
+    "name": "技术分析师",
+    "role": "技术分析师",
+    "avatar": "technical",
+    "rank": 0,
+    "winRate": null,
+    "bull": {
+      "n": 0,
+      "win": 0,
+      "unknown": 0
+    },
+    "bear": {
+      "n": 0,
+      "win": 0,
+      "unknown": 0
+    },
+    "logs": [],
+    "signals": [],
+    "modelName": "deepseek-v3.2",
+    "modelProvider": "DASHSCOPE"
+  },
+  {
+    "agentId": "fundamentals_analyst",
+    "name": "基本面分析师",
+    "role": "基本面分析师",
+    "avatar": "fundamentals",
+    "rank": 0,
+    "winRate": null,
+    "bull": {
+      "n": 0,
+      "win": 0,
+      "unknown": 0
+    },
+    "bear": {
+      "n": 0,
+      "win": 0,
+      "unknown": 0
+    },
+    "logs": [],
+    "signals": [],
+    "modelName": "deepseek-v3.2",
+    "modelProvider": "DASHSCOPE"
+  },
+  {
+    "agentId": "valuation_analyst",
+    "name": "估值分析师",
+    "role": "估值分析师",
+    "avatar": "valuation",
+    "rank": 0,
+    "winRate": null,
+    "bull": {
+      "n": 0,
+      "win": 0,
+      "unknown": 0
+    },
+    "bear": {
+      "n": 0,
+      "win": 0,
+      "unknown": 0
+    },
+    "logs": [],
+    "signals": [],
+    "modelName": "deepseek-v3.2",
+    "modelProvider": "DASHSCOPE"
+  }
+]

runs/reload_demo/team_dashboard/stats.json

@@ -0,0 +1,18 @@
+{
+  "totalAssetValue": 250000.0,
+  "totalReturn": 0.0,
+  "cashPosition": 250000.0,
+  "tickerWeights": {},
+  "totalTrades": 0,
+  "winRate": 0.0,
+  "bullBear": {
+    "bull": {
+      "n": 0,
+      "win": 0
+    },
+    "bear": {
+      "n": 0,
+      "win": 0
+    }
+  }
+}

runs/reload_demo/team_dashboard/summary.json

@@ -0,0 +1,13 @@
+{
+  "totalAssetValue": 250000.0,
+  "totalReturn": 0.0,
+  "cashPosition": 250000.0,
+  "tickerWeights": {},
+  "totalTrades": 0,
+  "pnlPct": 0.0,
+  "balance": 250000.0,
+  "equity": [],
+  "baseline": [],
+  "baseline_vw": [],
+  "momentum": []
+}

runs/reload_demo/team_dashboard/trades.json

@@ -0,0 +1 @@
+[]