Reference

Capability matrix

Compare verified historical, running simulated, and broker-backed behavior.

This matrix describes current documented runtime paths, not a promise that every adapter implements every method. Historical below means the generic memory path, with Agent Lab-specific limits called out. Broker paper accounts belong in the broker-backed column.

CapabilityHistorical memory / Agent LabRunning simulated sessionBroker-backed session
DataSelected historical observations; Lab uses supported bar inputIncoming feed with runtime-specific initializationConfigured provider/feed; may differ from execution venue
Orders and fillsShared synthetic modelSynthetic model for the selected runtimeAdapter and broker own acceptance/fills
SJS main algorithmSupported with historical data/runtime constraintsSupportedSupported; payloads and reconciliation remain adapter-specific
SQX conditions/modelsSupported current grammar; no reliable text OR or parenthesesSame grammarSame grammar; actions still require supported execution paths
Native PineSupported subset over supplied historyIncremental native input; confirmation mattersNative intents use the STX bridge, not an independent broker engine
L3 deterministic hooks/policiesAvailableAvailableAvailable where the execution path invokes its gates
Real L3 provider callsDisabled in backtests and historical warmupAllowed after warmup when configured/authorizedAllowed after warmup when configured/authorized
Fake-provider decisionsAvailable for deterministic testsAvailableAvailable; fake output does not disable other strategy actions
External live warmupNot fetched by memory sessions; include initialization in selected windowRuntime-dependent preload; Pine default one hourRuntime-dependent preload; inspect actual data
Order-fill delay settingUsed by supported synthetic executionUsed by supported synthetic executionDoes not force broker fill timing
Intrabar paths, liquidity, partial fillsNot established by generic close-based fillsNot established by synthetic fillsVenue/adapter-dependent; reconcile actual outcomes
State across restartA new run starts a new instanceIn-memory state is not guaranteed durableIn-memory state can reset while account exposure remains
Stop/terminateCompletion or stop is not a universal flat guaranteeDoes not imply account-style cancel/closeOutstanding broker orders/positions can remain
ResultsSelected artifacts, not the entire runtime objectLive state plus available stored snapshotsRuntime records plus authoritative broker/account outcomes

Agent Lab scope

Agent Lab's current worker uses a generic memory run, accepts supported bar-only configurations, and rejects tick, book, book-heartbeat, interpolation, and unsupported specialized families including Polymarket. Other historical engine paths can have different capabilities.

The authoring assistant can help edit source and inspect runs; its connection is separate from real model calls inside an executing L3 strategy. Publishing a revision creates or updates an app, then launch happens separately.

Integration boundaries

Polymarket has dedicated simulated, historical, and broker runtime paths outside the generic Lab assumptions. Multi-app launch supports a constrained set of leader/follower combinations rather than arbitrary brokers and duplicate instruments.

Do not infer full Pine language or strategy-tester parity, exchange-calendar parity across all providers, or a universal modification API from a method name. Use the detailed guides for the target path.

Continue with backtesting limitations, Pine support, SQX conditions, Polymarket, and multiple apps.

On this page