Checks a proposed order against the house position and gross-exposure floors.
Boundary. Validates supplied numbers only; it cannot place, cancel or route an order and does not read broker state.
- Credits
- 0 credits. Runs locally over stdio or on the hosted endpoint.
- Data sent
- Hosted: the order, equity and current positions you pass. Local: nothing leaves your machine.
- Coverage
- Any symbol; the checker only sees the figures you supply.
- Refusal states
- REJECTED with the exact floor quoted for each violation.
- Next step
- warden.cost_check, then warden.explain_sizing.
Input schema
{
"properties": {
"order": {
"additionalProperties": true,
"description": "Proposed order: {symbol, notional, side: buy|sell}.",
"title": "Order",
"type": "object"
},
"equity": {
"description": "Account equity (base currency) used for the exposure floors.",
"exclusiveMinimum": 0,
"title": "Equity",
"type": "number"
},
"current_positions": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional {symbol: notional} map of current positions.",
"title": "Current Positions"
},
"floor_overrides": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional per-fund overrides {max_position_pct, max_gross_exposure_pct}; the response always reports the deviation from the house floors.",
"title": "Floor Overrides"
}
},
"required": [
"order",
"equity"
],
"title": "validate_orderArguments",
"type": "object"
}
Audits a feature manifest for lookahead leakage and point-in-time provenance violations.
Boundary. Audits the manifest you supply. It cannot see code or data you do not declare.
- Credits
- 0 credits.
- Data sent
- Hosted: the feature manifest you pass. Local: nothing leaves your machine.
- Coverage
- Features declared in the manifest.
- Refusal states
- Lists each leaking or unprovenanced feature; nothing is silently passed.
- Next step
- warden.validate_genome.
Input schema
{
"properties": {
"manifest": {
"description": "Feature manifest: [{name, source, value_ts, as_of}] to audit.",
"items": {
"additionalProperties": true,
"type": "object"
},
"title": "Manifest",
"type": "array"
},
"tape_started": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional tape start date (YYYY-MM-DD); features predating it are flagged.",
"title": "Tape Started"
},
"selected_symbols": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional challenger-selected symbols for the coverage check.",
"title": "Selected Symbols"
},
"snapshot_universe": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional archived snapshot universe to measure coverage against.",
"title": "Snapshot Universe"
}
},
"required": [
"manifest"
],
"title": "audit_featuresArguments",
"type": "object"
}
Converts a claimed gross edge into a net-of-cost figure under a pessimistic fill model.
Boundary. A cost calculation on supplied inputs. It is not a backtest and not a forecast.
- Credits
- 0 credits.
- Data sent
- Hosted: the edge and turnover inputs you pass. Local: nothing leaves your machine.
- Coverage
- Any strategy expressed as gross edge and turnover.
- Refusal states
- Reports NEGATIVE_AFTER_COSTS when the claimed edge does not survive costs.
- Next step
- warden.validate_order.
Input schema
{
"properties": {
"gross_edge_bps": {
"description": "Claimed gross edge in basis points before costs.",
"title": "Gross Edge Bps",
"type": "number"
},
"spread_bps": {
"description": "Average bid-ask spread in bps.",
"minimum": 0,
"title": "Spread Bps",
"type": "number"
},
"slippage_bps": {
"description": "Expected slippage in bps.",
"minimum": 0,
"title": "Slippage Bps",
"type": "number"
},
"adverse_selection_bps": {
"description": "Adverse-selection drag in bps.",
"minimum": 0,
"title": "Adverse Selection Bps",
"type": "number"
}
},
"required": [
"gross_edge_bps",
"spread_bps",
"slippage_bps",
"adverse_selection_bps"
],
"title": "cost_checkArguments",
"type": "object"
}
Validates a strategy parameter vector (genome) against the bounded schema and returns its canonical hash.
Boundary. Schema and bounds check only. A valid genome is not a good genome.
- Credits
- 0 credits.
- Data sent
- Hosted: the genome vector you pass. Local: nothing leaves your machine.
- Coverage
- The published genome schema.
- Refusal states
- valid_genome false with the list of schema errors.
- Next step
- warden.audit_features, then gym.probe_fragility.
Input schema
{
"properties": {
"genome": {
"additionalProperties": true,
"description": "Genome object (bounded schema, versioned).",
"title": "Genome",
"type": "object"
}
},
"required": [
"genome"
],
"title": "validate_genomeArguments",
"type": "object"
}
Walks through position sizing step by step, mirroring the live risk engine's sizing logic.
Boundary. Explains a sizing calculation. It does not recommend a position.
- Credits
- 0 credits.
- Data sent
- Hosted: the sizing inputs you pass. Local: nothing leaves your machine.
- Coverage
- Any symbol; inputs are supplied by you.
- Refusal states
- Returns the binding floor and the clipped size when a cap applies.
- Next step
- warden.validate_order.
Input schema
{
"properties": {
"equity": {
"description": "Account equity (base currency).",
"exclusiveMinimum": 0,
"title": "Equity",
"type": "number"
},
"atr_14": {
"description": "14-bar average true range of the instrument.",
"exclusiveMinimum": 0,
"title": "Atr 14",
"type": "number"
},
"close": {
"description": "Current close/reference price.",
"exclusiveMinimum": 0,
"title": "Close",
"type": "number"
},
"weekend_approaching": {
"default": false,
"description": "True when the position would be held into the weekend (gross headroom applies).",
"title": "Weekend Approaching",
"type": "boolean"
},
"gross_exposure": {
"default": 0,
"description": "Current portfolio gross exposure in currency.",
"minimum": 0,
"title": "Gross Exposure",
"type": "number"
},
"overnight_gap": {
"default": 0,
"description": "Expected overnight gap (price units); gaps above 1.2x ATR halve size.",
"minimum": 0,
"title": "Overnight Gap",
"type": "number"
},
"floor_overrides": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional per-fund overrides; deviation from house floors is reported.",
"title": "Floor Overrides"
}
},
"required": [
"equity",
"atr_14",
"close"
],
"title": "explain_sizingArguments",
"type": "object"
}
Deterministic promotion-readiness and prerequisite check for a challenger genome before spending credits on a hosted tournament run.
Boundary. Always INDETERMINATE_LOCAL. Promotion selection machinery (Deflated Sharpe, PBO cap, trials ledger) runs server-side only; this readiness check is free and unmetered.
- Credits
- 0 credits.
- Data sent
- Hosted: the challenger_genome (and optional champion_genome) you pass. Local: nothing leaves your machine.
- Coverage
- Genome v2 and v3 schemas plus Tier-A/B/C mutation diff against champion_genome.
- Refusal states
- INDETERMINATE_LOCAL with readiness_status, naming the exact statistical inputs that only the hosted tournament can supply.
- Next step
- tournament.submit.
Input schema
{
"properties": {
"challenger_genome": {
"additionalProperties": true,
"description": "The challenger genome under evaluation.",
"title": "Challenger Genome",
"type": "object"
},
"champion_genome": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional current champion genome; mutation tiers vs it are reported.",
"title": "Champion Genome"
}
},
"required": [
"challenger_genome"
],
"title": "request_promotion_verdictArguments",
"type": "object"
}
Computes constrained target weights using volatility-targeted dual momentum, hierarchical risk parity, or shrinkage mean-variance.
Boundary. Produces target weights from trailing bars only. It is not investment advice and does not place orders.
- Credits
- Hosted: 1 credit per call. Local: 0. Pro entitlement required.
- Data sent
- Hosted: symbols, method, risk caps and bars you pass. Local: nothing leaves your machine.
- Coverage
- Your supplied bars or the shared cache.
- Refusal states
- REJECTED when fewer than two symbols have at least 65 sessions of trailing bars.
- Next step
- warden.plan_rebalance.
Input schema
{
"properties": {
"candidates": {
"description": "Candidate risk assets: [{symbol, momentum_score, realized_vol_annual, above_trend_sma?, chandelier_triggered?, current_weight?}].",
"items": {
"additionalProperties": true,
"type": "object"
},
"title": "Candidates",
"type": "array"
},
"method": {
"default": "vol_target_momentum",
"description": "Allocation method: vol_target_momentum | hrp | mvo_shrinkage.",
"title": "Method",
"type": "string"
},
"cash_proxy_symbol": {
"default": "SGOV",
"description": "Defensive cash proxy ticker receiving unallocated weight.",
"title": "Cash Proxy Symbol",
"type": "string"
},
"cash_momentum_score": {
"default": 0,
"description": "Composite momentum score of the defensive cash proxy.",
"title": "Cash Momentum Score",
"type": "number"
},
"target_volatility": {
"default": 0.12,
"description": "Target annualized portfolio volatility (e.g. 0.12 for 12%).",
"exclusiveMinimum": 0,
"maximum": 1,
"title": "Target Volatility",
"type": "number"
},
"top_k": {
"default": 2,
"description": "Maximum number of active risk slots to select.",
"maximum": 20,
"minimum": 1,
"title": "Top K",
"type": "integer"
},
"turnover_cap": {
"default": 0.5,
"description": "Maximum one-way portfolio turnover fraction per rebalance.",
"exclusiveMinimum": 0,
"maximum": 1,
"title": "Turnover Cap",
"type": "number"
},
"floor_overrides": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional per-fund overrides {max_position_pct, max_gross_exposure_pct}.",
"title": "Floor Overrides"
}
},
"required": [
"candidates"
],
"title": "optimize_portfolioArguments",
"type": "object"
}
Generates a guarded rebalance execution plan from current holdings to target weights.
Boundary. Plans marketable limit collars and sell-before-buy sequencing on supplied numbers only; never connects to a broker or routes orders.
- Credits
- 0 credits. Runs locally over stdio or on the hosted endpoint.
- Data sent
- Hosted: equity, high-water mark, positions, target weights and quotes you pass. Local: nothing leaves your machine.
- Coverage
- Any portfolio supplied by you.
- Refusal states
- HALT_KILL_SWITCH on a 12% drawdown breach or feature PSI drift above 0.25; skips diffs under 3% of equity or wide spreads.
- Next step
- warden.validate_order.
Input schema
{
"properties": {
"equity": {
"description": "Current account equity in base currency.",
"exclusiveMinimum": 0,
"title": "Equity",
"type": "number"
},
"high_water_mark": {
"description": "Portfolio historical high-water mark equity.",
"exclusiveMinimum": 0,
"title": "High Water Mark",
"type": "number"
},
"target_weights": {
"additionalProperties": true,
"description": "Target portfolio weights {symbol: weight_fraction}.",
"title": "Target Weights",
"type": "object"
},
"current_positions": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional current position notionals {symbol: notional}.",
"title": "Current Positions"
},
"quotes": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional quote snapshot {symbol: {bid, ask} or {mid, spread_bps}}.",
"title": "Quotes"
},
"cash_proxy_symbol": {
"default": "SGOV",
"description": "Defensive cash sweep ticker.",
"title": "Cash Proxy Symbol",
"type": "string"
},
"max_drawdown_limit": {
"default": 0.12,
"description": "Maximum drawdown from high-water mark before circuit-breaker liquidation.",
"exclusiveMinimum": 0,
"maximum": 0.5,
"title": "Max Drawdown Limit",
"type": "number"
},
"drift_threshold": {
"default": 0.03,
"description": "Minimum weight drift fraction required to trigger a rebalance step.",
"maximum": 0.25,
"minimum": 0,
"title": "Drift Threshold",
"type": "number"
},
"max_spread_bps": {
"default": 15,
"description": "Maximum allowed bid-ask spread in bps before rejecting execution.",
"exclusiveMinimum": 0,
"title": "Max Spread Bps",
"type": "number"
},
"limit_collar_bps": {
"default": 10,
"description": "Marketable limit price collar around midprice in bps.",
"minimum": 0,
"title": "Limit Collar Bps",
"type": "number"
},
"feature_psi": {
"default": 0,
"description": "Optional Population Stability Index of input features (>0.25 halts risk additions).",
"minimum": 0,
"title": "Feature Psi",
"type": "number"
}
},
"required": [
"equity",
"high_water_mark",
"target_weights"
],
"title": "plan_rebalanceArguments",
"type": "object"
}
Pre-trade prop-firm evaluation compliance guard: checks daily drawdown floors, overall loss limits, consistency caps, and target-lock sizing tapers.
Boundary. Validates supplied account and trade numbers against prop-evaluation rules only; never connects to a broker or routes orders.
- Credits
- 0 credits. Runs locally over stdio or on the hosted endpoint.
- Data sent
- Hosted: the account equity, drawdown limits, and proposed trade risk you pass. Local: nothing leaves your machine.
- Coverage
- TwoStep and OneStep prop-challenge rule sets.
- Refusal states
- REJECTED when equity breaches the safe daily or overall stop, when today's profit hits the consistency lock, or when all-in trade risk exceeds remaining daily headroom.
- Next step
- gym.prop_challenge_sim.
Input schema
{
"properties": {
"initial_balance": {
"default": 100000,
"description": "Initial prop-challenge evaluation balance in USD.",
"exclusiveMinimum": 0,
"title": "Initial Balance",
"type": "number"
},
"current_equity": {
"default": 100000,
"description": "Current account equity in USD.",
"exclusiveMinimum": 0,
"title": "Current Equity",
"type": "number"
},
"prev_day_close_equity": {
"default": 100000,
"description": "Previous trading day's closing equity in USD.",
"exclusiveMinimum": 0,
"title": "Prev Day Close Equity",
"type": "number"
},
"largest_single_day_profit": {
"default": 0,
"description": "Largest realized single-day profit so far in the evaluation (USD).",
"minimum": 0,
"title": "Largest Single Day Profit",
"type": "number"
},
"proposed_risk_usd": {
"default": 0,
"description": "Optional proposed dollar stop-loss risk for the next trade.",
"minimum": 0,
"title": "Proposed Risk Usd",
"type": "number"
},
"proposed_notional_usd": {
"default": 0,
"description": "Optional proposed order notional in USD (used for spread/swap friction).",
"minimum": 0,
"title": "Proposed Notional Usd",
"type": "number"
},
"format_type": {
"default": "TwoStep",
"description": "Challenge format: 'TwoStep' (default 5% daily / 10% max loss) or 'OneStep' (4% daily / 6% max loss).",
"title": "Format Type",
"type": "string"
},
"daily_loss_limit_pct": {
"default": 0.05,
"description": "Hard daily drawdown limit fraction (e.g. 0.05 for 5%).",
"exclusiveMinimum": 0,
"maximum": 0.5,
"title": "Daily Loss Limit Pct",
"type": "number"
},
"max_loss_limit_pct": {
"default": 0.1,
"description": "Hard overall drawdown limit fraction (e.g. 0.10 for 10%).",
"exclusiveMinimum": 0,
"maximum": 0.5,
"title": "Max Loss Limit Pct",
"type": "number"
},
"profit_target_pct": {
"default": 0.08,
"description": "Phase profit target fraction (e.g. 0.08 for 8%).",
"exclusiveMinimum": 0,
"maximum": 0.5,
"title": "Profit Target Pct",
"type": "number"
},
"consistency_cap_pct": {
"default": 0.4,
"description": "Maximum single-day share of total profit allowed by consistency rules (e.g. 0.40 for 40%).",
"exclusiveMinimum": 0,
"maximum": 1,
"title": "Consistency Cap Pct",
"type": "number"
},
"spread_bps": {
"default": 2,
"description": "Estimated round-trip bid-ask spread in basis points.",
"minimum": 0,
"title": "Spread Bps",
"type": "number"
},
"overnight_swap_bps": {
"default": 0,
"description": "Estimated daily overnight financing/swap drag in basis points.",
"minimum": 0,
"title": "Overnight Swap Bps",
"type": "number"
},
"planned_hold_days": {
"default": 1,
"description": "Planned holding period in trading days.",
"maximum": 60,
"minimum": 1,
"title": "Planned Hold Days",
"type": "integer"
}
},
"title": "prop_challenge_checkArguments",
"type": "object"
}
Classifies portfolio risk posture (Normal, Cautious, Defensive, CrisisShield) from trailing volatility, efficiency ratio, and drawdown telemetry.
Boundary. Pure risk-budget governance on supplied trailing metrics; never emits price predictions or places orders.
- Credits
- 0 credits. Runs locally over stdio or on the hosted endpoint.
- Data sent
- Hosted: the trailing return, volatility, and drawdown percentages you pass. Local: nothing leaves your machine.
- Coverage
- Any portfolio or benchmark telemetry supplied by you.
- Refusal states
- Refuses non-positive stop-heat caps or negative volatility inputs.
- Next step
- warden.plan_rebalance.
Input schema
{
"properties": {
"benchmark_return_1d_pct": {
"default": 0,
"description": "Trailing 1-day benchmark return in percent (e.g. -1.25 for -1.25%).",
"title": "Benchmark Return 1D Pct",
"type": "number"
},
"benchmark_return_5d_pct": {
"default": 0,
"description": "Trailing 5-day benchmark return in percent.",
"title": "Benchmark Return 5D Pct",
"type": "number"
},
"realized_vol_20d_pct": {
"default": 15,
"description": "Trailing 20-day annualized realized volatility in percent.",
"minimum": 0,
"title": "Realized Vol 20D Pct",
"type": "number"
},
"efficiency_ratio_20d": {
"default": 0.3,
"description": "Trailing 20-day Kaufman efficiency ratio in [0.0, 1.0].",
"maximum": 1,
"minimum": 0,
"title": "Efficiency Ratio 20D",
"type": "number"
},
"account_daily_pnl_pct": {
"default": 0,
"description": "Current account daily PnL in percent.",
"title": "Account Daily Pnl Pct",
"type": "number"
},
"open_unrealized_pnl_pct": {
"default": 0,
"description": "Current open portfolio unrealized PnL in percent.",
"title": "Open Unrealized Pnl Pct",
"type": "number"
},
"base_max_stop_heat_pct": {
"default": 3.2,
"description": "Baseline maximum aggregate portfolio stop-heat percentage.",
"exclusiveMinimum": 0,
"maximum": 20,
"title": "Base Max Stop Heat Pct",
"type": "number"
}
},
"title": "defensive_postureArguments",
"type": "object"
}
audit.preflight
FreeLocalsince 0.7.0
Validates researcher backtest artifacts (CSV/Parquet/JSON returns, trades, benchmark, cost assumptions, and feature manifests) locally and builds the Coverage & Scope Matrix.
Boundary. Strictly local and free (0 credits). Tabular returns alone cannot prove absence of lookahead bias in underlying strategy code.
- Credits
- 0 credits.
- Data sent
- Nothing. 0 bytes leave your machine.
- Coverage
- CSV, Parquet, or JSON return series, trade logs, benchmark series, cost assumptions, and feature provenance manifests.
- Refusal states
- Flags duplicate timestamps, NaN returns, missing columns, or empty files before any quote or run.
- Next step
- audit.quote.
Input schema
{
"properties": {
"returns_path": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Path to CSV/Parquet/JSON strategy returns (columns: ts/date, strategy_return/return).",
"title": "Returns Path"
},
"returns_rows": {
"anyOf": [
{
"items": {
"additionalProperties": true,
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"description": "Inline list of strategy return rows [{ts, strategy_return}].",
"title": "Returns Rows"
},
"trades_path": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional path to CSV/Parquet/JSON trade records (ts, symbol, pnl_bps, position_pct).",
"title": "Trades Path"
},
"trades_rows": {
"anyOf": [
{
"items": {
"additionalProperties": true,
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional inline trade records [{ts, symbol, pnl_bps, position_pct}].",
"title": "Trades Rows"
},
"benchmark_path": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional path to CSV/Parquet/JSON benchmark return series.",
"title": "Benchmark Path"
},
"benchmark_rows": {
"anyOf": [
{
"items": {
"additionalProperties": true,
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional inline benchmark return rows [{ts, return}].",
"title": "Benchmark Rows"
},
"cost_assumptions_path": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional path to JSON execution cost assumptions {spread_bps, slippage_bps, adverse_selection_bps}.",
"title": "Cost Assumptions Path"
},
"cost_assumptions": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional inline execution cost assumptions dict.",
"title": "Cost Assumptions"
},
"features_manifest_path": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional path to JSON feature provenance manifest {as_of, features: [...]}.",
"title": "Features Manifest Path"
},
"features_manifest": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional inline feature provenance manifest dict.",
"title": "Features Manifest"
},
"strategy_name": {
"default": "candidate_strategy",
"description": "Human-readable strategy or experiment identifier.",
"title": "Strategy Name",
"type": "string"
}
},
"title": "audit_preflightArguments",
"type": "object"
}
Prices a validated preflight manifest and issues a deterministic execution plan, runtime estimate, credit/GBP quote, and input-bound approval_token.
Boundary. Never executes the audit or charges credits. Refuses to quote if preflight eligibility failed.
- Credits
- 0 credits to quote (0 credits for local audit execution; 20 credits if hosted mode is requested).
- Data sent
- Local: nothing. Hosted: preflight metadata only.
- Coverage
- Any eligible preflight_id or inline backtest artifacts.
- Refusal states
- PREFLIGHT_REFUSED when input validation failed.
- Next step
- audit.run.
Input schema
{
"properties": {
"preflight_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Preflight ID returned by `audit.preflight`.",
"title": "Preflight Id"
},
"mode": {
"default": "local",
"description": "Execution mode: 'local' (0 credits, £0.00) or 'hosted' (20 credits).",
"title": "Mode",
"type": "string"
},
"random_seeds": {
"anyOf": [
{
"items": {
"type": "integer"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"description": "Deterministic bootstrap seeds (default [0, 1, 2, 3, 4]).",
"title": "Random Seeds"
},
"returns_path": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional returns path if calling quote directly without preflight_id.",
"title": "Returns Path"
},
"returns_rows": {
"anyOf": [
{
"items": {
"additionalProperties": true,
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional inline returns rows if calling quote directly.",
"title": "Returns Rows"
},
"trades_path": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional trades path.",
"title": "Trades Path"
},
"trades_rows": {
"anyOf": [
{
"items": {
"additionalProperties": true,
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional inline trades rows.",
"title": "Trades Rows"
},
"benchmark_path": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional benchmark path.",
"title": "Benchmark Path"
},
"benchmark_rows": {
"anyOf": [
{
"items": {
"additionalProperties": true,
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional inline benchmark rows.",
"title": "Benchmark Rows"
},
"cost_assumptions_path": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional cost assumptions JSON path.",
"title": "Cost Assumptions Path"
},
"cost_assumptions": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional inline cost assumptions dict.",
"title": "Cost Assumptions"
},
"features_manifest_path": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional feature manifest JSON path.",
"title": "Features Manifest Path"
},
"features_manifest": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional inline feature manifest dict.",
"title": "Features Manifest"
},
"strategy_name": {
"default": "candidate_strategy",
"description": "Strategy identifier.",
"title": "Strategy Name",
"type": "string"
}
},
"title": "audit_quoteArguments",
"type": "object"
}
Executes the Quant Swarm Audit across sample power, pessimistic execution cost survival (1.0x/1.5x/2.0x), drawdown/regime profile, trade concentration, and feature leakage.
Boundary. Never charges for preflight refusals, schema errors, or idempotent retries. Local mode runs at 0 credits; hosted mode charges 20 credits.
- Credits
- 0 credits in local mode; 20 credits in hosted mode.
- Data sent
- Local: nothing. Hosted: only the preflight-previewed series after approval_token verification.
- Coverage
- All checks listed in the preflight Coverage & Scope Matrix.
- Refusal states
- PREFLIGHT_REFUSED, SPEND_CAP_EXCEEDED, APPROVAL_TOKEN_INVALID, or IDEMPOTENCY_KEY_CONFLICT (all 0 credits).
- Next step
- audit.report or audit.status.
Input schema
{
"properties": {
"approval_token": {
"description": "Input-bound approval_token returned by `audit.quote`.",
"title": "Approval Token",
"type": "string"
},
"idempotency_key": {
"description": "Caller-supplied idempotency key to prevent duplicate execution or billing on retries.",
"title": "Idempotency Key",
"type": "string"
},
"max_credits": {
"default": 0,
"description": "Hard spend cap in credits (0 for local runs; >=20 for hosted runs).",
"minimum": 0,
"title": "Max Credits",
"type": "integer"
},
"preflight_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Preflight ID returned by `audit.preflight`.",
"title": "Preflight Id"
},
"mode": {
"default": "local",
"description": "Execution mode: 'local' (0 credits) or 'hosted' (20 credits).",
"title": "Mode",
"type": "string"
},
"random_seeds": {
"anyOf": [
{
"items": {
"type": "integer"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"description": "Deterministic bootstrap seeds (must match the seeds used in `audit.quote`).",
"title": "Random Seeds"
},
"returns_path": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional returns path.",
"title": "Returns Path"
},
"returns_rows": {
"anyOf": [
{
"items": {
"additionalProperties": true,
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional inline returns rows.",
"title": "Returns Rows"
},
"trades_path": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional trades path.",
"title": "Trades Path"
},
"trades_rows": {
"anyOf": [
{
"items": {
"additionalProperties": true,
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional inline trades rows.",
"title": "Trades Rows"
},
"benchmark_path": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional benchmark path.",
"title": "Benchmark Path"
},
"benchmark_rows": {
"anyOf": [
{
"items": {
"additionalProperties": true,
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional inline benchmark rows.",
"title": "Benchmark Rows"
},
"cost_assumptions_path": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional cost assumptions JSON path.",
"title": "Cost Assumptions Path"
},
"cost_assumptions": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional inline cost assumptions dict.",
"title": "Cost Assumptions"
},
"features_manifest_path": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional feature manifest JSON path.",
"title": "Features Manifest Path"
},
"features_manifest": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional inline feature manifest dict.",
"title": "Features Manifest"
},
"strategy_name": {
"default": "candidate_strategy",
"description": "Strategy identifier.",
"title": "Strategy Name",
"type": "string"
}
},
"required": [
"approval_token",
"idempotency_key"
],
"title": "audit_runArguments",
"type": "object"
}
Read-only polling of an active or completed audit job using its job_id without triggering new runs or charges.
Boundary. Read-only status lookup; never mutates state or bills credits.
- Credits
- 0 credits.
- Data sent
- The job_id string.
- Coverage
- Any job_id created in the session.
- Refusal states
- Returns status=not_found if job_id is unknown.
- Next step
- audit.report.
Input schema
{
"properties": {
"job_id": {
"description": "Audit job_id returned by `audit.run`.",
"title": "Job Id",
"type": "string"
}
},
"required": [
"job_id"
],
"title": "audit_statusArguments",
"type": "object"
}
Generates the machine-readable JSON audit bundle, cryptographic reproducibility manifest, and standalone shareable HTML and Markdown reports.
Boundary. Diagnostic evidence only, not investment advice or a promotion verdict.
- Credits
- 0 credits.
- Data sent
- Nothing.
- Coverage
- Completed audit jobs.
- Refusal states
- Returns status=not_found if job_id does not exist.
- Next step
- audit.compare or tournament.submit.
Input schema
{
"properties": {
"job_id": {
"description": "Completed audit job_id returned by `audit.run`.",
"title": "Job Id",
"type": "string"
},
"output_html_path": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional file path to write the standalone shareable HTML audit report.",
"title": "Output Html Path"
},
"output_json_path": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional file path to write the machine-readable JSON audit bundle.",
"title": "Output Json Path"
},
"output_markdown_path": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional file path to write the Markdown audit report.",
"title": "Output Markdown Path"
}
},
"required": [
"job_id"
],
"title": "audit_reportArguments",
"type": "object"
}
Compares two completed audit bundles (before/after remediation or version A vs. version B) and outputs a structured diff of metrics and resolved/new warnings.
Boundary. Compares recorded audit bundles at 0 credits.
- Credits
- 0 credits.
- Data sent
- Nothing.
- Coverage
- Any two completed audit job_ids.
- Refusal states
- Returns status=not_found if either job_id is missing.
- Next step
- tournament.submit.
Input schema
{
"properties": {
"job_id_a": {
"description": "Baseline / before-remediation audit job_id.",
"title": "Job Id A",
"type": "string"
},
"job_id_b": {
"description": "Candidate / after-remediation audit job_id.",
"title": "Job Id B",
"type": "string"
},
"output_html_path": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional file path to write the standalone before/after comparison HTML report.",
"title": "Output Html Path"
}
},
"required": [
"job_id_a",
"job_id_b"
],
"title": "audit_compareArguments",
"type": "object"
}
features.build
ProHostedsince 0.4.0
Builds the exact feature vector for a symbol at a session date, with provenance for every field.
Boundary. Runs a no-lookahead guard. Fields without point-in-time evidence are returned as UNSCORABLE, never zero-filled.
- Credits
- 1 credit per hosted call. Pro entitlement required.
- Data sent
- Symbol and as_of date.
- Coverage
- Covered symbol universe.
- Refusal states
- UNSCORABLE per field where provenance is missing.
- Next step
- warden.audit_features.
Input schema
{
"properties": {
"symbol": {
"description": "Ticker symbol, e.g. AAPL.",
"title": "Symbol",
"type": "string"
},
"as_of": {
"description": "Point-in-time session date (YYYY-MM-DD); every feature is a causal recomputation at this date, never a later revision.",
"title": "As Of",
"type": "string"
}
},
"required": [
"symbol",
"as_of"
],
"title": "build_featuresArguments",
"type": "object"
}
Derived technical snapshot per symbol: trend, volatility, oscillator, volume and regime signals.
Boundary. Derived ratios and labels only; no raw provider quotes.
- Credits
- 1 relay call (free plan: 250 per month, 10 symbols per call).
- Data sent
- The symbols you ask about.
- Coverage
- Covered symbol universe; supply your own bars for other symbols.
- Refusal states
- Symbols outside coverage are reported, not estimated.
- Next step
- market.regime.
Input schema
{
"properties": {
"symbols": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional list of tickers to analyze via the shared cache/relay (default: none — supply symbols or your own bars).",
"title": "Symbols"
},
"bars": {
"anyOf": [
{
"items": {
"additionalProperties": true,
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional caller-supplied OHLCV rows [{symbol, ts, open, high, low, close, volume}] for symbols the shared cache does not carry.",
"title": "Bars"
}
},
"title": "market_pulseArguments",
"type": "object"
}
Derived sentiment snapshot for a symbol: headline count and an earnings flag.
Boundary. Counts and flags only; no headline text.
- Credits
- 1 relay call.
- Data sent
- The symbol you ask about.
- Coverage
- Covered symbol universe.
- Refusal states
- Reports missing coverage instead of returning a neutral value.
- Next step
- pit.analysis.
Input schema
{
"properties": {
"symbol": {
"description": "Ticker symbol, e.g. TSLA.",
"title": "Symbol",
"type": "string"
}
},
"required": [
"symbol"
],
"title": "sentiment_pulseArguments",
"type": "object"
}
Area-specific weather research for each symbol's operating footprint.
Boundary. Research context. Weather coverage is partial and the output is not a trading signal.
- Credits
- 1 relay call.
- Data sent
- The symbols you ask about.
- Coverage
- Symbols with a mapped operating footprint.
- Refusal states
- Reports symbols without a footprint mapping.
- Next step
- pit.analysis.
Input schema
{
"properties": {
"symbols": {
"description": "Tickers whose operating-area climate to research (registry-covered weather-exposed underlyings, or any ticker you supply `areas` for).",
"items": {
"type": "string"
},
"title": "Symbols",
"type": "array"
},
"areas": {
"anyOf": [
{
"items": {
"additionalProperties": true,
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional caller-supplied operating areas for underlyings outside the shipped registry: [{symbol, name?, lat, lon, weight?}]. Weather is fetched ONLY for these made/sold geographies — never the listing exchange or HQ city.",
"title": "Areas"
}
},
"required": [
"symbols"
],
"title": "climate_snapshotArguments",
"type": "object"
}
Tests whether an alternative-data signal is statistically real for a symbol, with an explicit verdict per family and horizon.
Boundary. Statistical significance is not future profitability. Verdicts describe a family's power across the universe, not a forecast for one name.
- Credits
- 1 relay call. Free plan answers in lite mode; full per-horizon detail needs a funded Pro entitlement.
- Data sent
- Symbols and as_of date.
- Coverage
- Point-in-time datasets dated by when they were publicly knowable. Live counts are shown on this page.
- Refusal states
- SIGNIFICANT, NOT SIGNIFICANT, NOT JUDGED (below the observation floor) and RESEARCH-ONLY (under 50% coverage).
- Next step
- features.build.
Input schema
{
"properties": {
"symbols": {
"description": "Underlying tickers to query (max 10). Results are per underlying.",
"items": {
"type": "string"
},
"title": "Symbols",
"type": "array"
},
"as_of": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Point-in-time cutoff (YYYY-MM-DD, default today): release points after this date are ignored.",
"title": "As Of"
},
"horizons": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"description": "Subset of the run's horizons, e.g. ['1d','1w','1m','6m'] (default: all).",
"title": "Horizons"
},
"only_significant": {
"default": false,
"description": "Only return families with at least one SIGNIFICANT horizon (counts still cover everything).",
"title": "Only Significant",
"type": "boolean"
},
"max_families": {
"default": 20,
"description": "Max families returned per underlying, most significant first (1-100).",
"maximum": 100,
"minimum": 1,
"title": "Max Families",
"type": "integer"
}
},
"required": [
"symbols"
],
"title": "pit_analysisArguments",
"type": "object"
}
cache.warm
ProLocalsince 0.4.0
Backfills history into the local cache for a universe of symbols.
Boundary. Fetches derived data into your cache. It does not redistribute provider data.
- Credits
- 1 relay call per request. Pro entitlement required.
- Data sent
- The symbols and history depth you request.
- Coverage
- Covered symbol universe; depth capped by plan.
- Refusal states
- ACCESS_REQUIRED or a 402 on the free plan or an exhausted pool.
- Next step
- gym.label_regimes.
Input schema
{
"properties": {
"universe": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional list of tickers to backfill (default: the swarm's 13-symbol universe).",
"title": "Universe"
},
"years": {
"default": 1,
"description": "Years of daily history to backfill (max limited by the plan's backfill window).",
"exclusiveMinimum": 0.1,
"maximum": 10,
"title": "Years",
"type": "number"
}
},
"title": "cache_warmArguments",
"type": "object"
}
cache.stats
FreeLocalsince 0.4.0
Inventory of the local cache: rows per symbol, session bounds, depth in weeks and API-call accounting.
Boundary. Reports local state only.
- Credits
- 0 credits.
- Data sent
- Nothing.
- Coverage
- Whatever is in your local cache.
- Refusal states
- Not applicable.
- Next step
- cache.warm.
Input schema
{
"properties": {},
"title": "cache_statsArguments",
"type": "object"
}
cache.offline
FreeLocalsince 0.4.0
Toggles cache-only mode: no network access, reads served from cache, fetches refused.
Boundary. Changes local behaviour only.
- Credits
- 0 credits.
- Data sent
- Nothing.
- Coverage
- Whatever is in your local cache.
- Refusal states
- Fetches are refused while offline mode is on.
- Next step
- cache.stats.
Input schema
{
"properties": {
"enabled": {
"description": "True = cache-only mode (no network; reads from cache, fetches refused).",
"title": "Enabled",
"type": "boolean"
}
},
"required": [
"enabled"
],
"title": "offline_modeArguments",
"type": "object"
}
Causal regime label per symbol: high volatility, drawdown, chop, melt-up or gap-heavy.
Boundary. Labels use trailing data only. A label is a description, not a prediction.
- Credits
- 1 relay call.
- Data sent
- The symbols you ask about.
- Coverage
- Covered symbol universe.
- Refusal states
- Reports insufficient history instead of guessing a label.
- Next step
- gym.label_regimes.
Input schema
{
"properties": {
"symbols": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional list of tickers to label via the shared cache/relay.",
"title": "Symbols"
},
"bars": {
"anyOf": [
{
"items": {
"additionalProperties": true,
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional caller-supplied OHLCV rows [{symbol, ts, open, high, low, close, volume}] for symbols the shared cache does not carry.",
"title": "Bars"
}
},
"title": "regime_snapshotArguments",
"type": "object"
}
Derived microstructure snapshot: order-flow imbalance and toxicity measures.
Boundary. Derived values only; no raw quotes.
- Credits
- 1 relay call. Pro entitlement required.
- Data sent
- The symbols you ask about.
- Coverage
- Covered symbol universe.
- Refusal states
- Reports missing coverage per symbol.
- Next step
- volume.forecast.
Input schema
{
"properties": {
"symbol": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Ticker to analyze (served from the shared cache/relay); omit when passing your own bars.",
"title": "Symbol"
},
"bars": {
"anyOf": [
{
"items": {
"additionalProperties": true,
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional caller-supplied OHLCV rows [{symbol, ts, open, high, low, close, volume}].",
"title": "Bars"
}
},
"title": "microstructure_snapshotArguments",
"type": "object"
}
Derived volume forecast expressed as a ratio to the trailing 20-session average.
Boundary. A statistical forecast. It is not a price prediction.
- Credits
- 1 relay call. Pro entitlement required.
- Data sent
- The symbols you ask about.
- Coverage
- Covered symbol universe.
- Refusal states
- Reports insufficient history.
- Next step
- market.screen.
Input schema
{
"properties": {
"symbol": {
"description": "Ticker to forecast (served from the shared cache/relay).",
"title": "Symbol",
"type": "string"
},
"horizon_bars": {
"default": 1,
"description": "Number of sessions ahead to forecast (1-10).",
"maximum": 10,
"minimum": 1,
"title": "Horizon Bars",
"type": "integer"
}
},
"required": [
"symbol"
],
"title": "volume_forecastArguments",
"type": "object"
}
Ranked, derived-only screen across a symbol list.
Boundary. Cross-sectional ranking, not a recommendation.
- Credits
- 1 relay call. Pro entitlement required.
- Data sent
- The symbol list.
- Coverage
- Covered symbol universe.
- Refusal states
- Reports symbols that could not be scored.
- Next step
- market.rank.
Input schema
{
"properties": {
"symbols": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"description": "List of tickers to screen (via the shared cache/relay); omit when passing your own bars.",
"title": "Symbols"
},
"bars": {
"anyOf": [
{
"items": {
"additionalProperties": true,
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional caller-supplied OHLCV rows [{symbol, ts, open, high, low, close, volume}].",
"title": "Bars"
},
"criteria": {
"default": "breakout",
"description": "Screen criterion: breakout | momentum | volume | anomaly.",
"title": "Criteria",
"type": "string"
}
},
"title": "screen_universeArguments",
"type": "object"
}
Cross-sectional percentile rank of one derived metric across a symbol list.
Boundary. A rank, not a signal to trade.
- Credits
- 1 relay call. Pro entitlement required.
- Data sent
- The symbol list and the metric name.
- Coverage
- Covered symbol universe.
- Refusal states
- Reports symbols that could not be ranked.
- Next step
- market.screen.
Input schema
{
"properties": {
"symbols": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"description": "List of tickers to rank (via the shared cache/relay); omit when passing your own bars.",
"title": "Symbols"
},
"bars": {
"anyOf": [
{
"items": {
"additionalProperties": true,
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional caller-supplied OHLCV rows [{symbol, ts, open, high, low, close, volume}].",
"title": "Bars"
},
"metric": {
"default": "momentum_20d",
"description": "Metric to rank by: momentum_20d | volume_ratio_20d | atr_pct | rsi_14.",
"title": "Metric",
"type": "string"
}
},
"title": "cross_sectional_rankArguments",
"type": "object"
}
Point-in-time institutional flow snapshot: dark-pool FINRA short-volume z-score, Form 4 insider net buy-sell ratio, 13F breadth and Congressional flow.
Boundary. Derived z-scores, ratios and buckets only, gated by filing date; never raw filing text or share counts.
- Credits
- 1 relay call. Pro entitlement required.
- Data sent
- The symbols and optional as_of date you ask about.
- Coverage
- Covered symbol universe and supplied bars.
- Refusal states
- Reports missing history instead of neutral-filling.
- Next step
- pit.analysis.
Input schema
{
"properties": {
"symbols": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional list of tickers to analyze via the shared cache/relay.",
"title": "Symbols"
},
"bars": {
"anyOf": [
{
"items": {
"additionalProperties": true,
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional caller-supplied OHLCV rows [{symbol, ts, open, high, low, close, volume}].",
"title": "Bars"
},
"as_of": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional point-in-time cutoff date (YYYY-MM-DD).",
"title": "As Of"
}
},
"title": "market_flowArguments",
"type": "object"
}
Filing-date-gated SEC XBRL fundamentals and financial health scores: Piotroski F-Score, Altman Z-Score, accruals quality and gross profitability.
Boundary. Derived accounting ratios and health buckets only, strictly gated by public filing date.
- Credits
- 1 relay call. Pro entitlement required.
- Data sent
- The symbols and optional as_of date you ask about.
- Coverage
- Covered symbol universe and supplied bars.
- Refusal states
- Reports insufficient history instead of estimating missing fundamentals.
- Next step
- market.screen.
Input schema
{
"properties": {
"symbols": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional list of tickers to evaluate via the shared cache/relay.",
"title": "Symbols"
},
"bars": {
"anyOf": [
{
"items": {
"additionalProperties": true,
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional caller-supplied OHLCV rows [{symbol, ts, open, high, low, close, volume}].",
"title": "Bars"
},
"as_of": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional point-in-time cutoff date (YYYY-MM-DD); records after this date are masked.",
"title": "As Of"
}
},
"title": "market_fundamentals_pitArguments",
"type": "object"
}
Point-in-time macroeconomic regime nowcast: yield-curve slope, credit-spread z-score, VIX term structure, real-rate proxy and shipping stress.
Boundary. Derived macro regime z-scores and classifications only, gated by release date.
- Credits
- 1 relay call. Pro entitlement required.
- Data sent
- Optional as_of date and optional cross-asset bars.
- Coverage
- Point-in-time macro series and cross-asset proxies.
- Refusal states
- Reports proxy fallback when point-in-time macro series are absent from the local cache.
- Next step
- market.regime.
Input schema
{
"properties": {
"symbols": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional universe of tickers used to estimate breadth and dispersion.",
"title": "Symbols"
},
"bars": {
"anyOf": [
{
"items": {
"additionalProperties": true,
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional caller-supplied OHLCV rows [{symbol, ts, open, high, low, close, volume}].",
"title": "Bars"
},
"as_of": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional point-in-time cutoff date (YYYY-MM-DD).",
"title": "As Of"
}
},
"title": "market_macro_nowcastArguments",
"type": "object"
}
Pairwise directional Shannon transfer entropy and lead-lag matrix across a symbol basket.
Boundary. Quantized ternary return transfer entropy in bits; describes trailing directional coupling, not a price forecast.
- Credits
- 1 relay call. Pro entitlement required.
- Data sent
- The symbol list, lag and window parameters.
- Coverage
- Your supplied bars or the shared cache (2 to 15 symbols).
- Refusal states
- Refuses baskets with fewer than two aligned symbols or insufficient overlapping sessions.
- Next step
- warden.optimize_portfolio.
Input schema
{
"properties": {
"symbols": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"description": "Tickers (at least 2) to test for directed lead-lag information flow.",
"title": "Symbols"
},
"bars": {
"anyOf": [
{
"items": {
"additionalProperties": true,
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional caller-supplied OHLCV rows [{symbol, ts, open, high, low, close, volume}].",
"title": "Bars"
},
"window": {
"default": 60,
"description": "Trailing session window for transfer entropy estimation (25-252).",
"maximum": 252,
"minimum": 25,
"title": "Window",
"type": "integer"
}
},
"title": "market_transfer_entropyArguments",
"type": "object"
}
Point-in-time filing-gated insider cluster activity buckets, institutional accumulation percentiles, stealth absorption, and flow-price divergence z-scores.
Boundary. Derived percentiles, z-scores, and buckets only, gated by filing date; never echoes raw share counts or dollar figures.
- Credits
- 1 relay call. Pro entitlement required.
- Data sent
- The symbols and optional as_of date you ask about.
- Coverage
- Covered symbol universe and supplied bars.
- Refusal states
- Reports INSUFFICIENT_HISTORY when fewer than 20 sessions precede as_of.
- Next step
- market.supply_chain_pit.
Input schema
{
"properties": {
"symbols": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional list of tickers to evaluate via the shared cache/relay.",
"title": "Symbols"
},
"bars": {
"anyOf": [
{
"items": {
"additionalProperties": true,
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional caller-supplied OHLCV rows [{symbol, ts, open, high, low, close, volume}].",
"title": "Bars"
},
"as_of": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional point-in-time cutoff date (YYYY-MM-DD); records after this date are masked.",
"title": "As Of"
}
},
"title": "market_insider_institutional_pitArguments",
"type": "object"
}
Point-in-time freight/volume velocity percentiles, cross-border session flow percentiles, margin resilience, and pre-earnings supply-chain conviction buckets.
Boundary. Derived percentiles and conviction buckets only, gated by as_of; never echoes raw provider series.
- Credits
- 1 relay call. Pro entitlement required.
- Data sent
- The symbols and optional as_of date you ask about.
- Coverage
- Covered symbol universe and supplied bars.
- Refusal states
- Reports INSUFFICIENT_HISTORY when fewer than 20 sessions precede as_of.
- Next step
- market.climate.
Input schema
{
"properties": {
"symbols": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional list of tickers to evaluate via the shared cache/relay.",
"title": "Symbols"
},
"bars": {
"anyOf": [
{
"items": {
"additionalProperties": true,
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional caller-supplied OHLCV rows [{symbol, ts, open, high, low, close, volume}].",
"title": "Bars"
},
"as_of": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional point-in-time cutoff date (YYYY-MM-DD).",
"title": "As Of"
}
},
"title": "market_supply_chain_pitArguments",
"type": "object"
}
Labels causal market regimes over cached bars and reports the episode pool per regime, flagging thin pools.
Boundary. Labels use trailing data only; thin pools are flagged UNDERPOWERED.
- Credits
- Hosted: 1 credit per call. Local: 0.
- Data sent
- Hosted: symbols or bars you pass. Local: nothing leaves your machine.
- Coverage
- Your supplied bars or the shared cache.
- Refusal states
- UNDERPOWERED flags where the episode pool is thin.
- Next step
- gym.probe_fragility.
Input schema
{
"properties": {
"symbols": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional tickers served from the shared cache; omit when passing your own bars.",
"title": "Symbols"
},
"bars": {
"anyOf": [
{
"items": {
"additionalProperties": true,
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional inline OHLCV rows [{symbol, ts, open, high, low, close, volume}].",
"title": "Bars"
},
"min_symbols": {
"default": 8,
"description": "Minimum symbols required for a valid episode pool.",
"maximum": 20,
"minimum": 1,
"title": "Min Symbols",
"type": "integer"
}
},
"title": "label_regimesArguments",
"type": "object"
}
Replays a genome over a capped episode-seed matrix and reports per-regime fragility.
Boundary. Local previews are capped and labelled underpowered. Never a promotion verdict.
- Credits
- Hosted: 1 credit per simulated episode (5 regimes x per_regime x seeds). Local: 0.
- Data sent
- Hosted: the genome vector and bars you pass. Local: nothing leaves your machine.
- Coverage
- Your supplied bars or the shared cache.
- Refusal states
- UNDERPOWERED below 20 episodes; hard-constraint and lookahead violations are listed.
- Next step
- gym.paired_preview.
Input schema
{
"properties": {
"genome": {
"additionalProperties": true,
"description": "Genome to replay over the capped episode-seed matrix.",
"title": "Genome",
"type": "object"
},
"champion_genome": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional champion genome; tier-B/C mutations vs it refuse to score.",
"title": "Champion Genome"
},
"seeds": {
"anyOf": [
{
"items": {
"type": "integer"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional episode seeds (max 8 locally).",
"title": "Seeds"
},
"per_regime": {
"default": 2,
"description": "Episodes per regime (1 or 2 locally).",
"maximum": 2,
"minimum": 1,
"title": "Per Regime",
"type": "integer"
},
"symbols": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional tickers from the shared cache; omit when passing bars.",
"title": "Symbols"
},
"bars": {
"anyOf": [
{
"items": {
"additionalProperties": true,
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional inline OHLCV rows.",
"title": "Bars"
},
"min_symbols": {
"default": 8,
"description": "Minimum symbols for a valid episode pool.",
"maximum": 20,
"minimum": 1,
"title": "Min Symbols",
"type": "integer"
}
},
"required": [
"genome"
],
"title": "probe_fragilityArguments",
"type": "object"
}
Paired champion-versus-challenger preview on identical market paths.
Boundary. A preview on a capped matrix. It does not issue a promotion verdict.
- Credits
- Hosted: 1 credit per episode (doubled for two genomes). Local: 0.
- Data sent
- Hosted: the genome vectors you pass. Local: nothing leaves your machine.
- Coverage
- Your supplied bars or the shared cache.
- Refusal states
- UNDERPOWERED below 20 paired episodes.
- Next step
- tournament.submit.
Input schema
{
"properties": {
"champion_genome": {
"additionalProperties": true,
"description": "Current champion genome.",
"title": "Champion Genome",
"type": "object"
},
"challenger_genome": {
"additionalProperties": true,
"description": "Challenger genome to compare against the champion.",
"title": "Challenger Genome",
"type": "object"
},
"seeds": {
"anyOf": [
{
"items": {
"type": "integer"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional episode seeds (max 8 locally).",
"title": "Seeds"
},
"per_regime": {
"default": 2,
"description": "Episodes per regime (1 or 2 locally).",
"maximum": 2,
"minimum": 1,
"title": "Per Regime",
"type": "integer"
},
"symbols": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional tickers from the shared cache; omit when passing bars.",
"title": "Symbols"
},
"bars": {
"anyOf": [
{
"items": {
"additionalProperties": true,
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional inline OHLCV rows.",
"title": "Bars"
},
"min_symbols": {
"default": 8,
"description": "Minimum symbols for a valid episode pool.",
"maximum": 20,
"minimum": 1,
"title": "Min Symbols",
"type": "integer"
}
},
"required": [
"champion_genome",
"challenger_genome"
],
"title": "paired_previewArguments",
"type": "object"
}
Prices a hosted run before you spend credits.
Boundary. An estimate from the published rate card, not a quote for other work.
- Credits
- Hosted: 1 credit per call. Local: 0.
- Data sent
- Hosted: seeds, per_regime and genome count.
- Coverage
- Not applicable.
- Refusal states
- Rejects geometries above the caps.
- Next step
- gym.probe_fragility.
Input schema
{
"properties": {
"seeds": {
"anyOf": [
{
"items": {
"type": "integer"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional episode seeds (default [0..4]).",
"title": "Seeds"
},
"per_regime": {
"default": 4,
"description": "Episodes per regime (default 4 on the hosted side).",
"maximum": 10,
"minimum": 1,
"title": "Per Regime",
"type": "integer"
},
"n_genomes": {
"default": 1,
"description": "Number of genomes in the run.",
"maximum": 100,
"minimum": 1,
"title": "N Genomes",
"type": "integer"
}
},
"title": "estimate_cloud_runArguments",
"type": "object"
}
Validates and replays an ExpressionGraph (strategy-spec-v3) DAG across the five causal market regimes.
Boundary. Local runs are seed-capped and labelled UNDERPOWERED. Never issues a promotion verdict.
- Credits
- Hosted: 1 credit per simulated episode (5 regimes x per_regime x seeds). Local: 0.
- Data sent
- Hosted: the ExpressionGraph dict and bars you pass. Local: nothing leaves your machine.
- Coverage
- Your supplied bars or the shared cache.
- Refusal states
- INVALID_GRAPH on cycles, missing inputs or unsupported operators; UNDERPOWERED below 20 episodes.
- Next step
- gym.probe_fragility.
Input schema
{
"properties": {
"graph": {
"additionalProperties": true,
"description": "ExpressionGraph (strategy-spec-v3) DAG with nodes and output_node.",
"title": "Graph",
"type": "object"
},
"seeds": {
"anyOf": [
{
"items": {
"type": "integer"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional episode seeds (max 8 locally).",
"title": "Seeds"
},
"per_regime": {
"default": 2,
"description": "Episodes per regime (1 or 2 locally).",
"maximum": 2,
"minimum": 1,
"title": "Per Regime",
"type": "integer"
},
"symbols": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional tickers from the shared cache; omit when passing bars.",
"title": "Symbols"
},
"bars": {
"anyOf": [
{
"items": {
"additionalProperties": true,
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional inline OHLCV rows.",
"title": "Bars"
},
"min_symbols": {
"default": 8,
"description": "Minimum symbols for a valid episode pool.",
"maximum": 20,
"minimum": 1,
"title": "Min Symbols",
"type": "integer"
}
},
"required": [
"graph"
],
"title": "evaluate_graphArguments",
"type": "object"
}
Monte Carlo prop-firm challenge survival and optimal risk-sizing simulator across up to 500 multi-day evaluation paths.
Boundary. Simulates caller-supplied trade payoff distributions under prop-firm drawdown and consistency rules; never guarantees future evaluation outcomes.
- Credits
- Hosted: 1 credit per call. Local: 0. Pro entitlement required.
- Data sent
- Hosted: the trade R-multiples or win/loss parameters and rule thresholds you pass. Local: nothing leaves your machine.
- Coverage
- Caller-supplied trade R-multiples (5+) or parametric win-rate and payoff ratios.
- Refusal states
- Refuses fewer than 5 supplied trade R-multiples or out-of-range risk fractions.
- Next step
- warden.prop_challenge_check.
Input schema
{
"properties": {
"trades_r": {
"anyOf": [
{
"items": {
"type": "number"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional list of historical trade R-multiples (min 5) to bootstrap from; omit to use parametric win_rate/avg_win_r/avg_loss_r.",
"title": "Trades R"
},
"win_rate": {
"default": 0.52,
"description": "Win probability in [0.01, 0.99] when trades_r is omitted.",
"maximum": 0.99,
"minimum": 0.01,
"title": "Win Rate",
"type": "number"
},
"avg_win_r": {
"default": 1.85,
"description": "Average winning trade R-multiple when trades_r is omitted.",
"exclusiveMinimum": 0,
"title": "Avg Win R",
"type": "number"
},
"avg_loss_r": {
"default": 1,
"description": "Average losing trade R-multiple magnitude when trades_r is omitted.",
"exclusiveMinimum": 0,
"title": "Avg Loss R",
"type": "number"
},
"trades_per_day": {
"default": 2,
"description": "Average number of trades executed per trading session.",
"maximum": 20,
"minimum": 1,
"title": "Trades Per Day",
"type": "integer"
},
"risk_pct_per_trade": {
"default": 0.0075,
"description": "Fraction of equity risked per trade (e.g. 0.0075 for 0.75%).",
"maximum": 0.05,
"minimum": 0.0005,
"title": "Risk Pct Per Trade",
"type": "number"
},
"initial_balance": {
"default": 100000,
"description": "Starting prop-challenge balance in USD.",
"exclusiveMinimum": 0,
"title": "Initial Balance",
"type": "number"
},
"format_type": {
"default": "TwoStep",
"description": "Challenge format: 'TwoStep' or 'OneStep'.",
"title": "Format Type",
"type": "string"
},
"daily_loss_limit_pct": {
"default": 0.05,
"description": "Daily drawdown limit fraction (e.g. 0.05 for 5%).",
"exclusiveMinimum": 0,
"maximum": 0.5,
"title": "Daily Loss Limit Pct",
"type": "number"
},
"max_loss_limit_pct": {
"default": 0.1,
"description": "Overall max drawdown limit fraction (e.g. 0.10 for 10%).",
"exclusiveMinimum": 0,
"maximum": 0.5,
"title": "Max Loss Limit Pct",
"type": "number"
},
"profit_target_pct": {
"default": 0.08,
"description": "Phase profit target fraction (e.g. 0.08 for 8%).",
"exclusiveMinimum": 0,
"maximum": 0.5,
"title": "Profit Target Pct",
"type": "number"
},
"consistency_cap_pct": {
"default": 0.4,
"description": "Max single-day profit share allowed by consistency rules (e.g. 0.40 for 40%).",
"exclusiveMinimum": 0,
"maximum": 1,
"title": "Consistency Cap Pct",
"type": "number"
},
"max_trading_days": {
"default": 30,
"description": "Evaluation horizon in trading days.",
"maximum": 90,
"minimum": 1,
"title": "Max Trading Days",
"type": "integer"
},
"challenge_fee_usd": {
"default": 500,
"description": "Prop evaluation fee in USD used to compute expected net value.",
"minimum": 0,
"title": "Challenge Fee Usd",
"type": "number"
},
"payout_split_pct": {
"default": 0.8,
"description": "Trader profit split fraction upon passing (e.g. 0.80 for 80%).",
"exclusiveMinimum": 0,
"maximum": 1,
"title": "Payout Split Pct",
"type": "number"
},
"n_paths": {
"default": 250,
"description": "Number of Monte Carlo evaluation paths to simulate (1-500).",
"maximum": 500,
"minimum": 1,
"title": "N Paths",
"type": "integer"
},
"seed": {
"default": 42,
"description": "Deterministic RNG seed.",
"title": "Seed",
"type": "integer"
}
},
"title": "prop_challenge_simArguments",
"type": "object"
}
Evaluates a caller-supplied symbolic formula causally with a strict no-lookahead truncation guard, reporting Spearman rank IC, Newey-West HAC t-stat, and quantile spread.
Boundary. Evaluates only caller-supplied expressions on your panel window; never exposes internal formulas or issues local promotion verdicts.
- Credits
- Hosted: 1 credit per call. Local: 0. Pro entitlement required.
- Data sent
- Hosted: the symbolic formula string and symbols/bars you pass. Local: nothing leaves your machine.
- Coverage
- Your supplied bars or the shared cache (minimum 2 symbols).
- Refusal states
- Refuses unsupported AST operators, single-symbol inputs, or degenerate constant cross-sections.
- Next step
- tournament.submit.
Input schema
{
"properties": {
"formula": {
"description": "Caller-supplied symbolic expression using causal operators (CS_ZScore, CS_Rank, CS_Winsorize, TS_Mean, TS_Std, TS_Delta, TS_Corr, KaufmanER, Ret, Abs, Sign) and variables (ret1d, ret5d, ret20d, close, volume, vol_ratio), e.g. 'CS_ZScore(TS_Mean(ret1d, 10) * KaufmanER(10))'.",
"title": "Formula",
"type": "string"
},
"symbols": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional list of tickers (min 2) via the shared cache/relay.",
"title": "Symbols"
},
"bars": {
"anyOf": [
{
"items": {
"additionalProperties": true,
"type": "object"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional caller-supplied OHLCV rows [{symbol, ts, open, high, low, close, volume}].",
"title": "Bars"
},
"forward_horizon_days": {
"default": 5,
"description": "Forward return horizon in trading sessions (1-20).",
"maximum": 20,
"minimum": 1,
"title": "Forward Horizon Days",
"type": "integer"
}
},
"required": [
"formula"
],
"title": "evaluate_formulaArguments",
"type": "object"
}
tournament.submit
ProHostedsince 0.4.0
Submits a genome to the hosted Shadow Tournament: a paired replay against the swarm's champion on identical market paths.
Boundary. Returns a paired statistical outcome. A win is not a promotion, a league seat or a forecast of future returns.
- Credits
- 200 credits, or 100 with contribute=true. Pro entitlement required.
- Data sent
- The genome vector, its hash and the contribute flag. Never symbols, bars, features, orders or code unless you opt into the strategy tier.
- Coverage
- The hosted daily-bar panel.
- Refusal states
- ACCESS_REQUIRED or a 402 with the reason; failed runs refund the credits.
- Next step
- tournament.verdict.
Input schema
{
"properties": {
"genome": {
"additionalProperties": true,
"description": "Genome parameter vector (public schema) to score against the swarm's live champion. Validate locally with warden.validate_genome first.",
"title": "Genome",
"type": "object"
},
"contribute": {
"default": false,
"description": "true: license the genome vector + outcome to the swarm's evolution loop as an external challenger and pay half price. Combine with `disclosure` and/or `strategy_code` for the strategy-contributor tier (leaderboard attribution + league-seat eligibility after review). false (default): the vector is deleted after scoring; only hash + outcome remain.",
"title": "Contribute",
"type": "boolean"
},
"disclosure": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"description": "Strategy-contributor tier: author-written decision-logic disclosure (version 1; fields hypothesis, universe, selection, entry_timing, risk_sizing, weekend_hold, expected_edge — describe how the strategy decides, never code, data dumps, or secrets). Requires contribute=true. Validated locally before anything is sent.",
"title": "Disclosure"
},
"strategy_code": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Strategy-contributor tier: submit strategy CODE for STATIC LLM review. The code is treated as inert text — it is NEVER executed by us or the swarm; the hosted reviewer reads it with an LLM and stores only the structured explanation + a code hash (raw code is discarded after review). Remove keys/secrets first. Requires contribute=true.",
"title": "Strategy Code"
}
},
"required": [
"genome"
],
"title": "tournament_submitArguments",
"type": "object"
}
tournament.verdict
ProHostedsince 0.4.0
Polls a Shadow Tournament job and returns the paired outcome against the champion.
Boundary. Outcome is CHALLENGER_BEATS_CHAMPION, CHALLENGER_LOSES or INCONCLUSIVE. None of them is a promotion.
- Credits
- 0 credits. Pro entitlement required.
- Data sent
- The job id.
- Coverage
- Not applicable.
- Refusal states
- Pending or failed job states are reported as such.
- Next step
- tournament.leaderboard.
Input schema
{
"properties": {
"job_id": {
"description": "job_id returned by tournament.submit.",
"title": "Job Id",
"type": "string"
}
},
"required": [
"job_id"
],
"title": "tournament_verdictArguments",
"type": "object"
}
Anonymised Shadow Tournament board: champion rating and top challengers by ELO.
Boundary. Hashes are truncated and anonymised. Ratings describe replay results.
- Credits
- 0 credits. Free on every plan.
- Data sent
- Nothing.
- Coverage
- All completed tournament runs.
- Refusal states
- Not applicable.
- Next step
- tournament.submit.
Input schema
{
"properties": {},
"title": "tournament_leaderboardArguments",
"type": "object"
}
Read-only settlement ledger for the 8-week SHA-256 pre-committed Forward League and anonymised live multi-sleeve benchmarks.
Boundary. Exposes 12-char genome hash prefixes, Friday SHA-256 commitment hashes, realized net-of-cost return deltas, and sleeve risk-posture states only — never genome vectors, symbols, or equations.
- Credits
- 0 credits. Free on every plan.
- Data sent
- Nothing beyond optional boolean filter.
- Coverage
- Settled 8-week Batch 01 (2026-09-14 to 2026-11-09) and 3 live benchmark sleeves.
- Refusal states
- None.
- Next step
- tournament.submit.
Input schema
{
"properties": {
"include_weekly_commits": {
"default": true,
"description": "Include the week-by-week Friday SHA-256 pre-commitment settlement rows.",
"title": "Include Weekly Commits",
"type": "boolean"
}
},
"title": "tournament_forward_leagueArguments",
"type": "object"
}