crowd_simulation

Multi-persona crowd-simulation arena. Ingests a document, runs MiroFish for persona reactions, synthesises a CrowdPrediction via Ollama Cloud (deep tier).

manual

Phase Pipeline

ingest_input

sequential

→

run_mirofish_sim

sequential

→

aggregate_personas

sequential

→

synthesize

sequential

synthesis_agent

→

emit

sequential

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": "Multi-persona crowd-simulation arena. Ingests a document, runs MiroFish for persona reactions, synthesises a CrowdPrediction via Ollama Cloud (deep tier).",
  "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": 4096,
        "model": "auto",
        "temperature": 0.2
      }
    },
    "quick_model": "auto",
    "quick_provider": "ollama"
  },
  "max_iterations": 1,
  "memory": {
    "chromadb_path": "./data/chromadb",
    "embedding_model": "text-embedding-004",
    "embedding_provider": "gemini",
    "instances": []
  },
  "name": "crowd_simulation",
  "output_stream": "maf:arena:crowd_simulation:output",
  "phases": [
    {
      "agents": [],
      "max_rounds": 1,
      "name": "ingest_input",
      "pattern": "sequential",
      "signal_extract": false,
      "transition": "run_mirofish_sim"
    },
    {
      "agents": [],
      "max_rounds": 1,
      "name": "run_mirofish_sim",
      "pattern": "sequential",
      "signal_extract": false,
      "transition": "aggregate_personas"
    },
    {
      "agents": [],
      "max_rounds": 1,
      "name": "aggregate_personas",
      "pattern": "sequential",
      "signal_extract": false,
      "transition": "synthesize"
    },
    {
      "agents": [
        {
          "applicable_target_types": [],
          "extra": {},
          "llm_tier": "deep",
          "max_react_steps": 5,
          "name": "synthesis_agent",
          "role": "synthesis",
          "sources": [],
          "system_prompt": "",
          "tools": []
        }
      ],
      "max_rounds": 1,
      "name": "synthesize",
      "pattern": "sequential",
      "signal_extract": false,
      "transition": "emit"
    },
    {
      "agents": [],
      "max_rounds": 1,
      "name": "emit",
      "pattern": "sequential",
      "signal_extract": false,
      "transition": "END"
    }
  ],
  "sources": [
    {
      "adapter": "mirofish_crowd",
      "applicable_target_types": [],
      "config": {
        "base_url": "http://localhost:5101",
        "enabled": true,
        "offline_fixture": "tests/fixtures/mirofish_canned_report.json",
        "poll_interval_s": 5,
        "request_timeout_s": 30,
        "total_timeout_s": 1800
      },
      "name": "crowd_sim"
    }
  ],
  "target_key": "ticker",
  "triggers": []
}

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

Source Name	Adapter	Module	Parameters	Used By
crowd_sim	mirofish_crowd	mirofish	—	—

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

Loading memory data...

crowd_simulation

Phase Pipeline

ingest_input

run_mirofish_sim

aggregate_personas

synthesize

emit

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