edge-signal-aggregator

Edge Signal Aggregator

概述

将多个上游边缘机会发现技能的输出合并到一个加权信念度仪表板中。此技能会应用可配置的信号权重、去重重叠主题、标记不同技能之间的矛盾，并根据综合置信度得分对复合边缘机会创意进行排名。最终结果是一个优先级排序的边缘机会候选清单，并附有指向各贡献技能的来源链接。

适用场景

• 运行多个边缘机会发现技能后，希望获得统一视图
• 整合 edge-candidate-agent、theme-detector、sector-analyst 和 institutional-flow-tracker 的信号
• 在依据多个信号来源做出投资组合配置决策之前
• 识别不同分析方法之间的矛盾
• 确定哪些边缘机会创意值得深入研究

前置条件

• Python 3.9+
• 无需 API 密钥（处理其他技能生成的本地 JSON/YAML 文件）
• 依赖项：pyyaml（大多数环境中均为标准配置）

工作流

步骤 1：收集上游技能的输出

收集要汇总的上游技能输出文件：

• reports/edge_candidate_*.json，来自 edge-candidate-agent
• reports/edge_concepts_*.yaml，来自 edge-concept-synthesizer
• reports/theme_detector_*.json，来自 theme-detector
• reports/sector_analyst_*.json，来自 sector-analyst
• reports/institutional_flow_*.json，来自 institutional-flow-tracker
• reports/edge_hints_*.yaml，来自 edge-hint-extractor

步骤 2：运行信号汇总

执行汇总脚本，并传入上游输出文件的路径：

python3 skills/edge-signal-aggregator/scripts/aggregate_signals.py \
  --edge-candidates reports/edge_candidate_agent_*.json \
  --edge-concepts reports/edge_concepts_*.yaml \
  --themes reports/theme_detector_*.json \
  --sectors reports/sector_analyst_*.json \
  --institutional reports/institutional_flow_*.json \
  --hints reports/edge_hints_*.yaml \
  --output-dir reports/

可选：使用自定义权重配置：

python3 skills/edge-signal-aggregator/scripts/aggregate_signals.py \
  --edge-candidates reports/edge_candidate_agent_*.json \
  --weights-config skills/edge-signal-aggregator/assets/custom_weights.yaml \
  --output-dir reports/

步骤 3：查看汇总仪表板

打开生成的报告，查看：

1. 边缘机会创意排名 - 按综合信念度得分排序
2. 信号来源 - 哪些技能为每个创意提供了信息
3. 矛盾 - 标记相互冲突的信号，以便人工审核
4. 去重日志 - 合并的重叠主题

步骤 4：处理高信念度信号

按最低信念度阈值筛选候选清单：

python3 skills/edge-signal-aggregator/scripts/aggregate_signals.py \
  --edge-candidates reports/edge_candidate_agent_*.json \
  --min-conviction 0.7 \
  --output-dir reports/

输出格式

JSON 报告

{
  "schema_version": "1.0",
  "generated_at": "2026-03-02T07:00:00Z",
  "config": {
    "weights": {
      "edge_candidate_agent": 0.25,
      "edge_concept_synthesizer": 0.20,
      "theme_detector": 0.15,
      "sector_analyst": 0.15,
      "institutional_flow_tracker": 0.15,
      "edge_hint_extractor": 0.10
    },
    "min_conviction": 0.5,
    "dedup_similarity_threshold": 0.8
  },
  "summary": {
    "total_input_signals": 42,
    "unique_signals_after_dedup": 28,
    "contradictions_found": 3,
    "signals_above_threshold": 12
  },
  "ranked_signals": [
    {
      "rank": 1,
      "signal_id": "sig_001",
      "title": "AI Infrastructure Capex Acceleration",
      "composite_score": 0.87,
      "contributing_skills": [
        {
          "skill": "edge_candidate_agent",
          "signal_ref": "ticket_2026-03-01_001",
          "raw_score": 0.92,
          "weighted_contribution": 0.23
        },
        {
          "skill": "theme_detector",
          "signal_ref": "theme_ai_infra",
          "raw_score": 0.85,
          "weighted_contribution": 0.13
        }
      ],
      "tickers": ["NVDA", "AMD", "AVGO"],
      "direction": "LONG",
      "time_horizon": "3-6 months",
      "confidence_breakdown": {
        "multi_skill_agreement": 0.30,
        "signal_strength": 0.35,
        "recency": 0.22
      }
    }
  ],
  "contradictions": [
    {
      "contradiction_id": "contra_001",
      "description": "Conflicting sector view on Energy",
      "skill_a": {
        "skill": "sector_analyst",
        "signal": "Energy sector bearish rotation",
        "direction": "SHORT"
      },
      "skill_b": {
        "skill": "institutional_flow_tracker",
        "signal": "Heavy institutional buying in XLE",
        "direction": "LONG"
      },
      "resolution_hint": "Check timeframe mismatch (short-term vs long-term)"
    }
  ],
  "deduplication_log": [
    {
      "merged_into": "sig_001",
      "duplicates_removed": ["theme_detector:ai_compute", "edge_hints:datacenter_demand"],
      "similarity_score": 0.92
    }
  ]
}

Markdown 报告

Markdown 报告提供便于阅读的仪表板：

# Edge Signal Aggregator Dashboard
**Generated:** 2026-03-02 07:00 UTC

## Summary
- Total Input Signals: 42
- Unique After Dedup: 28
- Contradictions: 3
- High Conviction (>0.7): 12

## Top 10 Edge Ideas by Conviction

### 1. AI Infrastructure Capex Acceleration (Score: 0.87)
- **Tickers:** NVDA, AMD, AVGO
- **Direction:** LONG | **Horizon:** 3-6 months
- **Contributing Skills:**
  - edge-candidate-agent: 0.92 (ticket_2026-03-01_001)
  - theme-detector: 0.85 (theme_ai_infra)
- **Confidence Breakdown:** Agreement 0.30 | Strength 0.35 | Recency 0.22

...

## Contradictions Requiring Review

### Energy Sector Conflict
- **sector-analyst:** Bearish rotation (SHORT)
- **institutional-flow-tracker:** Heavy buying XLE (LONG)
- **Hint:** Check timeframe mismatch

## Deduplication Summary
- 14 signals merged into 8 unique themes
- Average similarity of merged signals: 0.89

报告保存在 reports/ 中，文件名为：

• edge_signal_aggregator_YYYY-MM-DD_HHMMSS.json
• edge_signal_aggregator_YYYY-MM-DD_HHMMSS.md

资源

• scripts/aggregate_signals.py -- 带有 CLI 界面的主要汇总脚本
• references/signal-weighting-framework.md -- 默认权重和评分方法的依据
• assets/default_weights.yaml -- 默认技能权重配置

核心原则

1. 来源追踪 -- 每个汇总后的信号都链接回其来源技能和原始引用
2. 矛盾透明 -- 标记而非隐藏相互冲突的信号，以便做出知情决策
3. 权重可配置 -- 默认权重反映了通常的可靠性，但可根据用户需求自定义
4. 去重但不丢失信息 -- 合并后的信号保留对所有原始来源的引用
5. 输出可执行 -- 提供排序列表，并为每个创意清晰列出股票代码、方向和时间范围