report_to_action

Fast-path arena: takes a fomo2 markdown report (or any structured analysis), runs three specialist views in parallel (signals, news/sentiment, risk), then synthesises a single BUY/HOLD/SELL action. The output is a structured TradingAction published to maf:actions:out — trtools2 picks it up and executes/queues/logs per ``action_mode`` (auto/semi/manual). Trigger paths: - control plane: XADD maf:control:in {command: run_arena, args: {arena: report_to_action, target: {ticker: NVDA, ...}, action_mode: "semi"}} - dashboard: POST /api/arenas/report_to_action/run - CLI: python -m maf trigger report_to_action --ticker NVDA --action-mode semi

manual

Phase Pipeline

analysis

parallel

signal_analyst (3 tools)

sentiment_analyst (3 tools)

risk_analyst (2 tools)

earnings_reviewer (6 tools)

→

synthesis

sequential

synthesis_agent

Ticker

Date

Configure the arena's metadata, data sources, agents and phases. Changes write to the YAML file. Restart the app to apply.

Metadata

Description One-line summary shown on the dashboard. Schedule Cron expression. Leave blank for manual-only runs. Max iterations How many replan loops are allowed before giving up. Target key Drives which outbox publishes the verdict.

Data sources

Bind data adapters to symbolic names. Agents reference these names in their sources list.

Agents

Each agent runs a ReAct loop, calls its bound sources as tools, and emits a structured signal.

Phases

Phases run in order. parallel fans out specialists, sequential runs one-by-one, debate does N-way rounds + judge.

Smart triggers

Auto-run this arena when a Redis Stream event matches a rule. Rules run through safe_eval (boolean/comparisons, abs(), payload.field). Reference →

Ticker

Start Date

End Date

Edit arena configuration (JSON). Changes write to YAML file — restart to apply.

{
  "applicable_target_types": [],
  "description": "Fast-path arena: takes a fomo2 markdown report (or any structured analysis),\nruns three specialist views in parallel (signals, news/sentiment, risk), then\nsynthesises a single BUY/HOLD/SELL action. The output is a structured\nTradingAction published to maf:actions:out \u2014 trtools2 picks it up and\nexecutes/queues/logs per ``action_mode`` (auto/semi/manual).\n\nTrigger paths:\n  - control plane: XADD maf:control:in {command: run_arena,\n      args: {arena: report_to_action, target: {ticker: NVDA, ...},\n             action_mode: \"semi\"}}\n  - dashboard: POST /api/arenas/report_to_action/run\n  - CLI: python -m maf trigger report_to_action --ticker NVDA --action-mode semi\n",
  "llm": {
    "deep_model": "auto",
    "deep_provider": "ollama",
    "default_provider": "ollama",
    "providers": {
      "ollama": {
        "api_key": "529224e623bb4df6bd2d35ca70830b11.1OcHilLKpOBPZbD1VizrA21P",
        "base_url": "https://ollama.com/v1",
        "max_output_tokens": 8192,
        "model": "auto",
        "temperature": 0.3
      }
    },
    "quick_model": "auto",
    "quick_provider": "ollama"
  },
  "max_iterations": 1,
  "memory": {
    "chromadb_path": "./data/chromadb",
    "embedding_model": "text-embedding-004",
    "embedding_provider": "gemini",
    "instances": [
      {
        "name": "synthesis_bm25",
        "persist_path": "",
        "type": "bm25"
      }
    ]
  },
  "name": "report_to_action",
  "output_stream": "maf:arena:report_to_action:output",
  "phases": [
    {
      "agents": [
        {
          "applicable_target_types": [],
          "extra": {},
          "llm_tier": "quick",
          "max_react_steps": 3,
          "name": "signal_analyst",
          "role": "specialist",
          "sources": [
            "report",
            "indicators",
            "strategy_events"
          ],
          "system_prompt": "",
          "system_prompt_file": "src/maf/arenas/trading_intelligence/prompts/market_analyst.txt",
          "tools": []
        },
        {
          "applicable_target_types": [],
          "extra": {},
          "llm_tier": "quick",
          "max_react_steps": 3,
          "name": "sentiment_analyst",
          "role": "specialist",
          "sources": [
            "latest_news",
            "enriched_items",
            "deep_data_request"
          ],
          "system_prompt": "",
          "system_prompt_file": "src/maf/arenas/trading_intelligence/prompts/news_analyst.txt",
          "tools": []
        },
        {
          "applicable_target_types": [],
          "extra": {},
          "llm_tier": "quick",
          "max_react_steps": 2,
          "name": "risk_analyst",
          "role": "specialist",
          "sources": [
            "indicators",
            "strategy_events"
          ],
          "system_prompt": "",
          "system_prompt_file": "src/maf/arenas/trading_intelligence/prompts/risk_analyst.txt",
          "tools": []
        },
        {
          "applicable_target_types": [],
          "extra": {},
          "llm_tier": "deep",
          "max_react_steps": 5,
          "name": "earnings_reviewer",
          "role": "specialist",
          "sources": [
            "latest_news",
            "deep_data_request",
            "indicators",
            "eodhd_fundamentals",
            "eodhd_earnings_calendar",
            "eodhd_news"
          ],
          "system_prompt": "",
          "system_prompt_file": "src/maf/prompts/anthropic_fs/agents/earnings_reviewer.md",
          "tools": []
        }
      ],
      "max_rounds": 1,
      "name": "analysis",
      "pattern": "parallel",
      "signal_extract": false,
      "transition": "synthesis"
    },
    {
      "agents": [
        {
          "applicable_target_types": [],
          "extra": {},
          "llm_tier": "deep",
          "max_react_steps": 5,
          "memory": "synthesis_bm25",
          "name": "synthesis_agent",
          "role": "synthesis",
          "sources": [],
          "system_prompt": "",
          "system_prompt_file": "src/maf/arenas/trading_intelligence/prompts/synthesis_agent.txt",
          "tools": []
        }
      ],
      "max_rounds": 1,
      "name": "synthesis",
      "pattern": "sequential",
      "signal_extract": false,
      "transition": "END"
    }
  ],
  "sources": [
    {
      "adapter": "fomo2_report",
      "applicable_target_types": [],
      "config": {
        "glob_pattern": "analyze_*.md",
        "max_chars_for_simulation": 8000,
        "output_dir": "../fomo2/output"
      },
      "name": "report"
    },
    {
      "adapter": "trtools2_news",
      "applicable_target_types": [],
      "config": {
        "count": 30,
        "stream": "trtools2:news"
      },
      "name": "latest_news"
    },
    {
      "adapter": "trtools2_indicators",
      "applicable_target_types": [],
      "config": {
        "count": 30,
        "stream": "trtools2:indicators"
      },
      "name": "indicators"
    },
    {
      "adapter": "trtools2_strategy_events",
      "applicable_target_types": [],
      "config": {
        "count": 20,
        "stream": "trtools2:strategy:events"
      },
      "name": "strategy_events"
    },
    {
      "adapter": "fomo2_items",
      "applicable_target_types": [],
      "config": {
        "count": 30
      },
      "name": "enriched_items"
    },
    {
      "adapter": "fomo2_request",
      "applicable_target_types": [],
      "config": {
        "wait": true,
        "wait_seconds": 20
      },
      "name": "deep_data_request"
    },
    {
      "adapter": "eodhd",
      "applicable_target_types": [],
      "config": {
        "tool": "get_fundamentals"
      },
      "name": "eodhd_fundamentals"
    },
    {
      "adapter": "eodhd",
      "applicable_target_types": [],
      "config": {
        "tool": "get_earnings_calendar"
      },
      "name": "eodhd_earnings_calendar"
    },
    {
      "adapter": "eodhd",
      "applicable_target_types": [],
      "config": {
        "tool": "get_news"
      },
      "name": "eodhd_news"
    }
  ],
  "target_key": "ticker",
  "triggers": []
}

Data sources bound to this arena. Agents access these via ReAct tool calls.

Source Name	Adapter	Module	Parameters	Used By
report	fomo2_report	fomo2	—	signal_analyst
latest_news	trtools2_news	trtools2	—	sentiment_analyst, earnings_reviewer
indicators	trtools2_indicators	trtools2	—	signal_analyst, risk_analyst, earnings_reviewer
strategy_events	trtools2_strategy_events	trtools2	—	signal_analyst, risk_analyst
enriched_items	fomo2_items	fomo2	—	sentiment_analyst
deep_data_request	fomo2_request	fomo2	—	sentiment_analyst, earnings_reviewer
eodhd_fundamentals	eodhd	trtools2	—	earnings_reviewer
eodhd_earnings_calendar	eodhd	trtools2	—	earnings_reviewer
eodhd_news	eodhd	trtools2	—	earnings_reviewer

Decision trail — every arena run is saved for review and auditing.

Loading memory data...

report_to_action

Phase Pipeline

analysis

synthesis

Agent Signals

Execution Trace

Source Monitoring

Agent Reports

Debates

Decisions

Target Context

Metadata

Data sources

Agents

Phases

Smart triggers

Performance Metrics

vs Buy & Hold

Equity Curve

Trades

Signal Timeline