Agents

Stream the analysis agent on a live question

Stream the agent's LLM forecast thesis while preserving the final report shape.

The fixed pipeline streams the underlying forecast generation as delta events, then emits the same structured AgentReport as /agent/analyze in done. Tool-loop mode remains available through the blocking endpoint because its model turns are interleaved with tool calls rather than one continuous answer.

post/agent/analyze/stream

Request

Base URL: https://foresea.ink (the document declares no server; this is the origin it was published from)
URL: https://foresea.ink/agent/analyze/stream
Auth: none declared

Request body

questionstring nullable

Market question. Optional if a market identifier is given.

platformstring nullable

'polymarket' or 'kalshi' to fetch a live price.

market_platformstring nullable

Prediction-market venue supplied by the forecasting UI.

market_identstring nullable

Polymarket slug or Kalshi ticker supplied by the forecasting UI.

market_urlstring nullable

slugstring nullable

Polymarket market slug.

market_idstring nullable

Polymarket numeric market id.

tickerstring nullable

Kalshi market ticker.

descriptionstring

resolution_criteriastring

categoriesstring[]

market_probabilitynumber nullable

Override market price (0..1 or 0..100) when not fetching.

market_bidnumber nullable

market_asknumber nullable

market_volumenumber nullable

market_liquiditynumber nullable

resolve_timestring nullable

variantstring

evidence_top_kinteger

builtin_skillsboolean

Also run the built-in forecasting toolkit (base rate, scenario decomposition, red team, key drivers).

ground_in_recordboolean

Condition the forecast on the model's own live track-record calibration.

tool_loopboolean

Use a ReAct tool-using loop (model plans + calls tools) instead of the fixed pipeline.

benchmark_toolsboolean

When tool_loop=true, expose Foresea's market-research toolkit. place_trade and manage_notes are reserved for Foresea's scheduled trading agents and are not available over the API.

benchmark_tool_namesstring[] nullable

When benchmark_tools=true, restrict the exposed tool set to named Foresea tools -- e.g. a research-only call passes ['web_search', 'orderbook'], a pure-reasoning call passes [] (no tools, so the model must answer on its first turn). Unset exposes every tool available to the caller. Naming place_trade or manage_notes over the API is refused with 403.

max_tool_stepsinteger

Max tool calls in the loop.

effort_tier'simple' | 'standard' | 'deep' nullable

How much analysis effort this question gets (evidence fetch depth, which built-in skills run, tool-loop step budget). Set explicitly to override; left unset, the server estimates it from the question.

historyobject[]

Prior conversation turns for follow-up context.

conversation_steerstring

Optional per-conversation steering instruction.

openrouter_api_keystring nullable

openrouter_modelstring nullable

modelstring nullable

provider_base_urlstring nullable

ollama_base_urlstring nullable

agent_profile_idstring nullable

Private copied-agent recipe. Its research model and instructions are server-resolved.

client_run_keystring nullable

Caller-supplied idempotency key, stored on the durable AgentRun this request creates. If your own request times out waiting for a response, the run may still be progressing server-side -- look it up with GET /agent/runs?client_run_key=... instead of restarting.

max_tokensinteger nullable

Max output tokens for the agent tool loop and skills.

Example request

{
  "news_articles": [
    {
      "publish_date": "2025-01-15T10:30:00Z",
      "relevance_score": 0.91,
      "source": "Reuters",
      "summary": "Federal Reserve officials signaled a more cautious approach to rate cuts...",
      "title": "Fed signals rate cuts may slow in 2025",
      "url": "https://reuters.com/example"
    }
  ]
}

Response

Server-sent events with forecast deltas and a final AgentReport payload.

unknown required

Changes

No recorded changes to this operation across all 1 revision of this API.