decker.close_position | Axis③ (Order/Execution) — closes (or partially reduces) an existing position through DECKER'S OWN execution engine (see decker.place_order for what that means — same account-linkage requirement applies here for real positions). Unlike place_order, there is no crypto-6 restriction — this reduces risk, not adds it, so any symbol you actually hold (including HL-synthetic/KRX paper positions) can be closed. Mode is NOT chosen by the caller — this looks up whatever position(s) actually exist for the symbol (real via live exchange query, virtual via the paper ledger) and closes whichever are open; if both a real and a virtual position exist for the same symbol, both are closed and the response reports execution_mode as 'mixed'. No open position for the symbol = a clean not-found response, not an error — safe to call speculatively. |
decker.get_assembly | Multi-timeframe path per symbol (STRATEGY_LAYER §8.4), built from the same per-timeframe judgment state as decker.get_market_state (CR1) — no weights, scores or thresholds. READ `verdict` FIRST: the one state + one action for the symbol right now (state = direction · phase; action = 진입 enter | 유지 hold | 청산 exit | 대기 wait, the engine's own action words; `reason` says why, `until` names the close that would change it). Everything below is supporting detail. frame = the highest timeframe with a confirmed signal (its side is the path direction; upper TF supplies direction and target, lower TF supplies the entry). Each timeframe row is classified frame | aligned | counter (confirmed, opposite side = a pullback in progress) | hint. grade = phase in plain words: 정렬 (no counter row) | 되돌림 (counter row exists, frame signal still alive) | 전환 시험 (frame signal is against / reversal pending) | 재장전 (no confirmed signal). entry = the lowest-timeframe aligned row whose signal is still alive (for/inside the signal bar), GO first; mode 지금 only when that signal's close is on its favorable side, otherwise 대기. stop/target/RR come from those rows' own coordinates. cond = the frame signal's fail edge (a close beyond it starts a reversal test). path = nearby price coordinates with what a close there means for the frame / entry piece / counter rows; onward = next targets in the path direction. watch = THE watch list, in time order: each upcoming bar close (timeframes closing at the same instant are one overlapping group) with every timeframe's state and the question that close decides — which side of which judged price (target, signal-bar edge, reversal-hold price) the close lands; a price also judged by a higher timeframe is flagged (this close is a hint for that one). summary_ko = ready-to-show Korean lines; ladder_upper / ladder_near = nearest coordinates (4h+ only / all timeframes) with `reads` and that timeframe's next close (KST); markers = which ladder point entry/stop/target sits on. Omit symbol for all 14 universe symbols. Narrate or filter the result — do not re-decide coordinates. ⚠ 정렬 does not mean every timeframe's gate is GO: check matrix_summary[].gate and .position. ⚠ entry.mode='지금' means the entry row's signal is on its favorable side now; it does NOT mean the engine confirmed a new event on this bar — check the entry row's gate. |
decker.get_engine_state_raw | [DEPRECATED — use decker.get_market_state (consumer contract CR1). Raw per-bar engine state dump (Market State v0); kept only for KRX symbols and will be removed.] |
decker.get_episodes | Price-axis EPISODE history — answers 'where did I buy/sell last time, what was the target value and the event chain then, and where did price move WITHOUT a signal (and which target values it passed = missing points)'. Read-only from the persisted event ledger (no recompute). `episodes` (newest first) = one target selection until the next: target {price, from_price, reason}, chain (primary-unit judgment events), signals {ts, side, entry, targets, resolved{status, close, bar_low, bar_high}}, left (target_left: MISSING = a target value price passed through with no judgment; MOVED), missing, signal_gap (no signal in that episode), move {start_close, end_close, pct}. `signal_gaps` (ascending) = the interval between consecutive signals with its price move and the missing points inside (last one is open). Missing points carry `sign` and `position` (price below/above the target at the pass) — classify on the read side; do not re-decide coordinates. History starts at the first persisted event of this generation. |
decker.get_market_state | Current swing-judgment state of a symbol across timeframes, as structured data (consumer contract CR1). Per timeframe (top→short): stage = target_selected (대상선정) | pending (판정보류: the close is still inside the signal bar) | confirmed (확인) | failed (실패) | none; side = buy/sell; signal_time; signal_bar {time, low, high} (the bar whose edges decide confirm/fail); confirmed_at / resolved_close; entry (= close at the signal, the fill basis); stop; target (the take-profit 목표가: opposite-side confirmed-signal edge at least 2% from entry, else null + target_reason; levels[].kind uses unit_target for the judged price, never `target`); unit_target (the price this timeframe is judging now = the 대상/anchor; NOT the take-profit — that is `target`); units = the targets this timeframe is watching together (max 6, primary first; secondary units judge concurrently when another earlier target is touched while the primary is judging): [{unit_target, zone buy|sell (buy = bought-from-below place, sell = sold-from-above place), stage target_selected|reverse_pending|confirmed|reverse_failed (추세 변경 안 됨), primary, touch_kind, touched_at, holds, reverse_side}] — not signals; reverse_pending = null, or {side, unit_target, holds, confirm, fail_side} when the reversal of that target is on hold (반전 보류: the first reversing key appeared but the next judgment bar has not yet closed beyond the target — side = the reversing side, independent of stage: a confirmed sell signal can coexist with a buy reversal on hold; fail_side = the key that would mean the target held and the move continues); prev_signal; standing = null, or {side, signal_time, entry, stop, target, target_rr}: the standing stance's reference signal while a new target is being selected (stage=target_selected after a confirmed signal) — the entry/stop/target of that confirmed signal, kept apart from the stage-bound entry/stop/target above (those stay null until a signal is current); turn = reverse (the signal flips the previous signal's direction = it changes the standing action) | same (continues it) | null; levels = nearby prices above/below the close. state_text = ready-to-show Korean status (title with price, then two compact lines: 상위·중간 / 단기, timeframes without a signal omitted, a failed row carries the price that decided it, plus nearby prices; no interpretation). Marks in state_text: color = state, shape = direction — 🟢▲ buy confirmed · 🔴▼ sell confirmed (action-worthy) · ⚪▲/⚪▼ pending (signal exists, unconfirmed) · 🟡 target selected / reversal on hold (반전 보류) · ✖️ failed (void signal, NOT the opposite side). timeframe_summary = the same rows merely listed by (stage, side), e.g. confirmed.buy = ['1d','4h'] (plus reverse_pending.buy/sell) — a listing, not a verdict: no weights, scores or votes, and failed is NOT counted as the opposite side. events = recent target_selected / signal / signal_resolved / reverse_failed (추세 변경 안 됨: the primary target's reversal attempt failed, side = the trend that holds, not a signal) / reverse_tested (반전 테스트: the first reversing key on the primary target; side = reversing side, status beyond = that key's close is past the target = minimum condition met, short = not; not a signal) / conn_arrival, newest first, always including each timeframe's own latest 2 events (so slow timeframes such as 1w/1d are not pushed out by 30m/1h activity; pass `timeframe` for one timeframe's full history). Each timeframe reports its own state side by side — there is NO cross-timeframe verdict, no probability/confidence/bias fields; combining timeframes into a view is the caller's job. HOW TO ANSWER: this tool is the source of truth for direction. Show state_text, then explain in your own words using only these values (what each timeframe confirmed/failed/is waiting on, and which prices to watch); do not invent probabilities or targets. decker.get_view shows the same values as ready-made text. Read as persisted (no recompute). layer=STATE: a market-state reading, NOT a trade instruction. Crypto and Hyperliquid synthetics only (KRX: use decker.get_reading). Before placing any order through any execution tool, check the intent with decker.validate_intent. |
decker.get_positions | Axis③ (Order/Execution) — this user's actual exposure: real open futures positions (execution_mode=real, with live sl_price/tp_price), virtual (paper) open positions, and the last 10 closed round-trips per mode. This is what your money actually did, distinct from decker.get_signals (axis②, what the engine recommends) — use this before deciding whether to place another order (avoid duplicate/over-exposure) and to check current protective stop/target on a real position. |
decker.get_price_axis_state | [DEPRECATED — use decker.get_market_state (CR1). Raw price-axis state dump; superseded and will be removed.] |
decker.get_reading | AI-synthesized market reading for a symbol/timeframe, in customer-facing language: current state description, directional bias scores, bidirectional break targets, MTF verdict per timeframe, and an execution hint (stance + long/short setups). Engine-native raw fields are NOT exposed here — use the REST raw contract (GET /public/reading) or decker.get_market_state for those . execution_hint.preferred_direction is derived from key_direction alone and is NOT guaranteed to have a matching long_setup/short_setup (they come from an independent break-target resolver) — check that the setup for the preferred side is non-null before treating preferred_direction as an actionable side. |
decker.get_signals | Active trading signals for the current user (with Skill Overlay applied), in customer-facing shape: coordinates (entry/target/stop), decision (ENTER/WAIT/SKIP — is_actual_trigger=true only for ENTER; WAIT/SKIP are standing candidates, not executed triggers), action_gate posture (GO/WATCH/HOLD — a stance, not an order command), progress, MTF verdict, and a plain-language summary_ko line. risk_reward_ratio is computed on the DISPLAYED coordinates (after overlay). Signals are retained rather than cut when they age (turn-retention policy) — read freshness_state (open|aged) / age_bars / freshness_sec before treating an old PENDING row as current. Filtered by symbols / min_progress / action_gate — action_gate here filters the CURRENT-MOMENT representative state, it does not search history (almost always 0 rows unless a gate is GO right now); for past GO events with their entry/target/stop and realized performance use decker.get_trigger_history instead. Before placing any order through any execution tool, check the intent with decker.validate_intent. |
decker.get_state_timeline | Market State v0 — per-bar state timeline for a symbol/timeframe (v0 per-bar schema — NOT the structured CR1 of decker.get_market_state; for the persisted event list use decker.get_market_state `events` or GET /public/state/{symbol}/{tf}/events; each item carries a SLIM `game` tag {status, target_id, zt_regime, provenance} instead of the full game block — read status transitions across bars to see how the target game unfolded (forming → testing → resolved/failed); ascending by bar_ts). Bars the engine did not emit are simply absent (honest gaps, no filling). |
decker.get_trigger_history | ACTION axis — actual historical GO triggers (not standing WATCH/HOLD candidates) for a symbol, with entry/target/stop coordinates and realized performance (mfe_pct/mae_pct/exit_reason/exit_price from trigger_performance, null = still open). Distinct from decker.get_signals (which reflects only the current-moment state, not a searchable history — its action_gate filter answers 'what does symbol×tf look like right now', not 'when did this last fire'). Use this to answer 'what did the engine actually trigger recently and at what price' — decker.get_signals/get_market_state cannot answer that. direction is judgment_signals-native vocabulary ("long"/"short"), distinct from the "+"/"-" convention used by other tools — read as-is, no translation. |
decker.get_user_skills | Trading skill catalog + currently active overlay for this user. Returns 8 published skills (conservative_v0/standard_v0/aggressive_v0/default_v0/scalp_v0/tight_v0/wide_v0/swing_v0) and the user's selected one. |
decker.get_view | Ready-to-show Korean status card for a symbol — the same card the daily briefing sends, built from the same consumer contract (CR1) as decker.get_market_state, so direction and prices always agree with it. Shows the timeframes grouped 상위/중간/단기 with one line each (direction + stage + the price that decided it), the nearby prices to watch, and a short explanation of the chosen timeframe (tf, default 4h): what closed beyond what, whether the signal flips the previous one, entry/target/stop. Also returns direction (+/- only while that timeframe's signal is pending or confirmed; a failed or absent signal gives no direction — failure does not assert the opposite side), wait_target, invalidation, ref_price and recent self-scoring verdicts. Use this when you want text to show as-is; use decker.get_market_state when you want structured values to reason over. layer=STATE_VIEW: a market-state reading, NOT a trade instruction. Before placing any order through any execution tool, check the intent with decker.validate_intent. |
decker.place_order | Axis③ (Order/Execution) — unlike every other tool here, this one moves money. It places a market order through DECKER'S OWN execution engine (same path as the decker-ai.com chat trading UI, source='mcp') — it does NOT hand off to your own broker connection or exchange account; Decker executes using whatever exchange credentials this user has separately linked to their Decker account on the website. execution_mode (virtual|real) is NOT chosen by the caller — it is resolved server-side from this user's account settings (user_settings.execution_mode) AND the platform's real-trading kill switch; a real-money order requires both an explicit user opt-in AND role/tier eligibility (PRO/ENTERPRISE or admin) AND passing the tier's hard notional/leverage/daily-count caps (checked here before dispatch — violation blocks the order, does not downgrade it to virtual). The response always states which mode actually executed — treat 'virtual' in the response as authoritative even if you expected real. Restricted to the crypto-6 universe (BTCUSDT/ETHUSDT/SOLUSDT/BNBUSDT/XRPUSDT/DOGEUSDT) for this MCP path — HL-synthetic and KRX symbols are read-only via other tools. Call decker.validate_intent first to read the engine's current stance; this tool does not check it for you. Positions are tracked as ONE net row per user+symbol+mode, not per order — if you already hold a position on this symbol, this order nets into it and the response's pre_existing_position field says so. A later close_position call closes the combined total, not just what this call added. |
decker.set_skill_overlay | Change active trading skill overlay for this user. Immediately affects all subsequent get_signals calls and downstream channels. |
decker.update_protective_stops | Axis③ (Order/Execution) — modifies the stop-loss and/or take-profit on an EXISTING open position. There is no cancel_order tool because Decker only places market orders (there is no resting order to cancel) — the actual gap this fills is modifying protective stops on a position you already hold. real: cancels the old exchange stop/take-profit order(s) and places new ones at the given price(s) (new order placed first, old one canceled only after — no unprotected window). virtual: updates the paper position's stop_loss/take_profit columns directly (polled by the paper monitor). Provide at least one of sl_price/tp_price — the other side, if omitted, is left at its current value. If both a real and a virtual position are open for this symbol, pass mode explicitly or the call is rejected asking which one. |
decker.validate_intent | Pre-trade gate check for a proposed order intent. Call this BEFORE placing any order through any execution tool (e.g. a broker MCP's review→place flow). Checks the intent (symbol + side) against Decker's deterministic market state: engine action_gate (GO/WATCH/HOLD — a transition posture, not an order command), current structural state, and the active signal's direction / invalidation (stop) coordinates. Returns a stance reading, NOT an approval or rejection: the vocabulary is the engine gate as-is plus a mechanical side_alignment (aligned/opposed vs the active signal's direction). covered=false means the engine does not emit state for this symbol — treat as unknown, not as HOLD. top-level action_gate can be null even when covered=true — this is not a missing field, it means the current bar has no fresh trigger reading; check gate_null_reason ('no_gate_available' = neither the current bar nor the carried-forward signal had a gate at all, vs 'signal_stale' = a value existed but the underlying signal exceeded the staleness threshold and was deliberately suppressed rather than served as a confident-but-old answer). The order decision and responsibility remain with the calling agent/user. Every check is persisted to an auditable decision ledger (check_id). |
protogrid