solana-traderclaw 1.0.59 → 1.0.60

package/config/gateway-v1-upgraded.json5

@@ -38,7 +38,7 @@
         agentId: "main",
         sessionTarget: "isolated",
         delivery: { mode: "none" },
-        message: "CRON_JOB: source_reputation_recalc\n\nStep 1: Call solana_alpha_sources to get per-source performance stats.\n\nStep 2: Call solana_alpha_history to get recent signal history.\n\nStep 3: Call solana_trades to get recent trade outcomes. Cross-reference each trade to its originating signal source.\n\nStep 4: For each source, calculate: win rate, average PnL, signal-to-trade conversion rate.\n\nStep 5: Assign tier rankings:\n- TIER-1 (LOCK): Win rate above 60% AND 5+ trades AND positive avg PnL\n- TIER-2 (CONDITIONAL): Win rate 30-60% OR fewer than 5 trades\n- TIER-3 (BLACKLIST): Win rate below 30% with 5+ trades\n\nStep 6: Write scorecard to memory using solana_memory_write with tag 'source_reputation'.\n\nFORMATTING RULES:\n- Every token reference MUST use SYMBOL (full_CA) format.\n- Do not execute trades. Do not ask questions.",
+        message: "CRON_JOB: source_reputation_recalc\n\nStep 1: Call solana_alpha_sources to get per-source performance stats (signal count, conversion rate, avg score).\n\nStep 2: Call solana_alpha_history to get recent signal history with scores and source identifiers.\n\nStep 3: Call solana_trades to get recent trade outcomes. Cross-reference each trade back to its originating signal source.\n\nStep 4: For each source, calculate: win rate (trades that hit TP vs SL), average PnL per trade, signal-to-trade conversion rate.\n\nStep 5: Assign tier rankings:\n- TIER-1 (LOCK): Win rate above 60% AND 5+ trades AND positive avg PnL\n- TIER-2 (CONDITIONAL): Win rate 30-60% OR fewer than 5 trades\n- TIER-3 (BLACKLIST): Win rate below 30% with 5+ trades\n\nStep 6: Write scorecard to memory using solana_memory_write with tag 'source_reputation'.\n\nFORMATTING RULES:\n- Every token reference MUST use SYMBOL (full_CA) format.\n- Do not execute trades. Do not ask questions.",
         enabled: true
       },
 
@@ -49,7 +49,7 @@
         agentId: "main",
         sessionTarget: "isolated",
         delivery: { mode: "none" },
-        message: "CRON_JOB: portfolio_risk_audit\n\nStep 1: Call solana_capital_status for wallet balance and portfolio value.\n\nStep 2: Call solana_positions for all open positions.\n\nStep 3: For each position, call solana_token_snapshot for current price and volume.\n\nStep 4: Run concentration check — flag WARNING if any position > 30% of portfolio, CRITICAL if > 50%.\n\nStep 5: Run exposure check — flag WARNING if total exposure > 50% of wallet, CRITICAL if > 75%.\n\nStep 6: Run drawdown check — CRITICAL if drawdown exceeds 25% from peak.\n\nStep 7: Calculate portfolio heat. Flag WARNING > 50%, CRITICAL > 75%.\n\nStep 8: Run liquidity check — WARNING if position > 2% of pool depth.\n\nStep 9: Check solana_killswitch_status.\n\nStep 10: Write risk report via solana_memory_write with tag 'risk_audit'.\n\nFORMATTING RULES:\n- Every token reference MUST use SYMBOL (full_CA) format.\n- Do not execute trades. Do not ask questions.",
+        message: "CRON_JOB: portfolio_risk_audit\n\nStep 1: Call solana_capital_status to get wallet balance and portfolio value.\n\nStep 2: Call solana_positions to get all open positions with entry prices and sizes.\n\nStep 3: For each open position, call solana_token_snapshot to get current price, 24h volume, and market cap.\n\nStep 4: Run concentration check — flag WARNING if any single position exceeds 30 percent of total portfolio value, CRITICAL if above 50 percent.\n\nStep 5: Run exposure check — flag WARNING if total exposure exceeds 50 percent of wallet balance, CRITICAL if above 75 percent.\n\nStep 6: Run drawdown check — CRITICAL if portfolio drawdown exceeds 25 percent from peak capital.\n\nStep 7: Calculate portfolio heat (sum of all position risk scores). Flag WARNING above 50 percent, CRITICAL above 75 percent.\n\nStep 8: Run liquidity check — WARNING if any position exceeds 2 percent of its pool depth.\n\nStep 9: Check solana_killswitch_status.\n\nStep 10: Write risk report via solana_memory_write with tag 'risk_audit'.\n\nFORMATTING RULES:\n- Every token reference MUST use SYMBOL (full_CA) format.\n- Do not execute trades. Do not ask questions.",
         enabled: true
       },
 
@@ -60,7 +60,7 @@
         agentId: "main",
         sessionTarget: "isolated",
         delivery: { mode: "none" },
-        message: "CRON_JOB: meta_rotation_analysis\n\nStep 1: Call solana_scan_launches to get recent launches (last 3-6 hours).\n\nStep 2: Categorize each token by narrative cluster: AI/Agents, Animal Memes, Political, Celebrity/IP, DeFi, Gaming, Culture/Humor, Other.\n\nStep 3: For each cluster, aggregate: token count, total volume, average market cap.\n\nStep 4: Call solana_memory_search for 'meta_rotation' to compare with prior scan.\n\nStep 5: Classify each narrative: GAINING, SATURATED, COOLING, DORMANT.\n\nStep 6: Write rotation report via solana_memory_write with tag 'meta_rotation'.\n\nFORMATTING RULES:\n- Every token reference MUST use SYMBOL (full_CA) format.\n- Do not execute trades. Do not ask questions.",
+        message: "CRON_JOB: meta_rotation_analysis\n\nStep 0: Call x_search_tweets with queries: 'solana memecoin', 'pump fun gem', 'sol alpha'. Note which token names and narratives appear most frequently in the last 3 hours. Use this social signal to validate or challenge the on-chain data in the following steps.\n\nStep 1: Call solana_scan_launches to get recent token launches (last 3-6 hours).\n\nStep 2: Categorize each token by narrative cluster: AI/Agents, Animal Memes, Political, Celebrity/IP, DeFi, Gaming, Culture/Humor, Other.\n\nStep 3: For each cluster, aggregate: token count, total volume, average market cap.\n\nStep 4: Call solana_memory_search for 'meta_rotation' to compare with prior scan.\n\nStep 5: Classify each narrative: GAINING, SATURATED, COOLING, DORMANT.\n\nStep 6: Write rotation report via solana_memory_write with tag 'meta_rotation'.\n\nFORMATTING RULES:\n- Every token reference MUST use SYMBOL (full_CA) format.\n- Do not execute trades. Do not ask questions.",
         enabled: true
       },
 
@@ -80,7 +80,7 @@
         agentId: "main",
         sessionTarget: "isolated",
         delivery: { mode: "none" },
-        message: "CRON_JOB: subscription_cleanup\n\nStep 1: Call solana_positions to get open position CAs.\n\nStep 2: Call solana_bitquery_subscriptions to list active subscriptions.\n\nStep 3: Build matched vs orphaned lists.\n\nStep 4: Unsubscribe orphans via solana_bitquery_unsubscribe.\n\nStep 5: Reopen subscriptions nearing 24h expiry via solana_bitquery_subscription_reopen.\n\nStep 6: Write summary via solana_memory_write with tag 'subscription_cleanup'.\n\nFORMATTING RULES:\n- Every token reference MUST use SYMBOL (full_CA) format.\n- Do not execute trades. Do not ask questions.",
+        message: "CRON_JOB: subscription_cleanup\n\nStep 1: Call solana_positions to get all open positions and extract their contract addresses.\n\nStep 2: Call solana_bitquery_subscriptions to list all active Bitquery subscriptions. If this call returns an AUTH_SCOPE_MISSING error, log the error to memory and stop gracefully — do not retry or error out.\n\nStep 3: For each active subscription, check if the associated token CA still has an open position. Build two lists: 'matched' (has position) and 'orphaned' (no position).\n\nStep 4: Unsubscribe orphans via solana_bitquery_unsubscribe.\n\nStep 5: Reopen subscriptions nearing 24h expiry via solana_bitquery_subscription_reopen.\n\nStep 6: Write summary via solana_memory_write with tag 'subscription_cleanup'.\n\nFORMATTING RULES:\n- Every token reference MUST use SYMBOL (full_CA) format.\n- Do not execute trades. Do not ask questions.",
         enabled: true
       },
 

package/config/gateway-v1.json5

@@ -38,7 +38,7 @@
         agentId: "main",
         sessionTarget: "isolated",
         delivery: { mode: "none" },
-        message: "CRON_JOB: source_reputation_recalc\n\nStep 1: Call solana_alpha_sources to get per-source performance stats.\n\nStep 2: Call solana_alpha_history to get recent signal history.\n\nStep 3: Call solana_trades to get recent trade outcomes. Cross-reference each trade to its originating signal source.\n\nStep 4: For each source, calculate: win rate, average PnL, signal-to-trade conversion rate.\n\nStep 5: Assign tier rankings:\n- TIER-1 (LOCK): Win rate above 60% AND 5+ trades AND positive avg PnL\n- TIER-2 (CONDITIONAL): Win rate 30-60% OR fewer than 5 trades\n- TIER-3 (BLACKLIST): Win rate below 30% with 5+ trades\n\nStep 6: Write scorecard to memory using solana_memory_write with tag 'source_reputation'.\n\nFORMATTING RULES:\n- Every token reference MUST use SYMBOL (full_CA) format.\n- Do not execute trades. Do not ask questions.",
+        message: "CRON_JOB: source_reputation_recalc\n\nStep 1: Call solana_alpha_sources to get per-source performance stats (signal count, conversion rate, avg score).\n\nStep 2: Call solana_alpha_history to get recent signal history with scores and source identifiers.\n\nStep 3: Call solana_trades to get recent trade outcomes. Cross-reference each trade back to its originating signal source.\n\nStep 4: For each source, calculate: win rate (trades that hit TP vs SL), average PnL per trade, signal-to-trade conversion rate.\n\nStep 5: Assign tier rankings:\n- TIER-1 (LOCK): Win rate above 60% AND 5+ trades AND positive avg PnL\n- TIER-2 (CONDITIONAL): Win rate 30-60% OR fewer than 5 trades\n- TIER-3 (BLACKLIST): Win rate below 30% with 5+ trades\n\nStep 6: Write scorecard to memory using solana_memory_write with tag 'source_reputation'.\n\nFORMATTING RULES:\n- Every token reference MUST use SYMBOL (full_CA) format.\n- Do not execute trades. Do not ask questions.",
         enabled: true
       },
 
@@ -49,7 +49,7 @@
         agentId: "main",
         sessionTarget: "isolated",
         delivery: { mode: "none" },
-        message: "CRON_JOB: portfolio_risk_audit\n\nStep 1: Call solana_capital_status for wallet balance and portfolio value.\n\nStep 2: Call solana_positions for all open positions.\n\nStep 3: For each position, call solana_token_snapshot for current price and volume.\n\nStep 4: Run concentration check — flag WARNING if any position > 30% of portfolio, CRITICAL if > 50%.\n\nStep 5: Run exposure check — flag WARNING if total exposure > 50% of wallet, CRITICAL if > 75%.\n\nStep 6: Run drawdown check — CRITICAL if drawdown exceeds 25% from peak.\n\nStep 7: Calculate portfolio heat. Flag WARNING > 50%, CRITICAL > 75%.\n\nStep 8: Run liquidity check — WARNING if position > 2% of pool depth.\n\nStep 9: Check solana_killswitch_status.\n\nStep 10: Write risk report via solana_memory_write with tag 'risk_audit'.\n\nFORMATTING RULES:\n- Every token reference MUST use SYMBOL (full_CA) format.\n- Do not execute trades. Do not ask questions.",
+        message: "CRON_JOB: portfolio_risk_audit\n\nStep 1: Call solana_capital_status to get wallet balance and portfolio value.\n\nStep 2: Call solana_positions to get all open positions with entry prices and sizes.\n\nStep 3: For each open position, call solana_token_snapshot to get current price, 24h volume, and market cap.\n\nStep 4: Run concentration check — flag WARNING if any single position exceeds 30 percent of total portfolio value, CRITICAL if above 50 percent.\n\nStep 5: Run exposure check — flag WARNING if total exposure exceeds 50 percent of wallet balance, CRITICAL if above 75 percent.\n\nStep 6: Run drawdown check — CRITICAL if portfolio drawdown exceeds 25 percent from peak capital.\n\nStep 7: Calculate portfolio heat (sum of all position risk scores). Flag WARNING above 50 percent, CRITICAL above 75 percent.\n\nStep 8: Run liquidity check — WARNING if any position exceeds 2 percent of its pool depth.\n\nStep 9: Check solana_killswitch_status.\n\nStep 10: Write risk report via solana_memory_write with tag 'risk_audit'.\n\nFORMATTING RULES:\n- Every token reference MUST use SYMBOL (full_CA) format.\n- Do not execute trades. Do not ask questions.",
         enabled: true
       },
 
@@ -80,7 +80,7 @@
         agentId: "main",
         sessionTarget: "isolated",
         delivery: { mode: "none" },
-        message: "CRON_JOB: subscription_cleanup\n\nStep 1: Call solana_positions to get open position CAs.\n\nStep 2: Call solana_bitquery_subscriptions to list active subscriptions.\n\nStep 3: Build matched vs orphaned lists.\n\nStep 4: Unsubscribe orphans via solana_bitquery_unsubscribe.\n\nStep 5: Reopen subscriptions nearing 24h expiry via solana_bitquery_subscription_reopen.\n\nStep 6: Write summary via solana_memory_write with tag 'subscription_cleanup'.\n\nFORMATTING RULES:\n- Every token reference MUST use SYMBOL (full_CA) format.\n- Do not execute trades. Do not ask questions.",
+        message: "CRON_JOB: subscription_cleanup\n\nStep 1: Call solana_positions to get all open positions and extract their contract addresses.\n\nStep 2: Call solana_bitquery_subscriptions to list all active Bitquery subscriptions. If this call returns an AUTH_SCOPE_MISSING error, log the error to memory and stop gracefully — do not retry or error out.\n\nStep 3: For each active subscription, check if the associated token CA still has an open position. Build two lists: 'matched' (has position) and 'orphaned' (no position).\n\nStep 4: Unsubscribe orphans via solana_bitquery_unsubscribe.\n\nStep 5: Reopen subscriptions nearing 24h expiry via solana_bitquery_subscription_reopen.\n\nStep 6: Write summary via solana_memory_write with tag 'subscription_cleanup'.\n\nFORMATTING RULES:\n- Every token reference MUST use SYMBOL (full_CA) format.\n- Do not execute trades. Do not ask questions.",
         enabled: true
       },
 

package/dist/{chunk-T4YWGIIR.js → chunk-VUIYNUGF.js}

@@ -26,7 +26,7 @@ async function doRequest(opts, isRetry = false) {
       headers,
       signal: controller.signal
     };
-    if ((opts.method === "POST" || opts.method === "PUT") && opts.body) {
+    if ((opts.method === "POST" || opts.method === "PUT" || opts.method === "PATCH") && opts.body) {
       fetchOpts.body = JSON.stringify(opts.body);
     }
     const res = await fetch(url, fetchOpts);

package/dist/index.js

@@ -18,7 +18,7 @@ import {
 } from "./chunk-3YPZOXWE.js";
 import {
   orchestratorRequest
-} from "./chunk-T4YWGIIR.js";
+} from "./chunk-VUIYNUGF.js";
 import {
   IntelligenceLab
 } from "./chunk-C24QA3MQ.js";
@@ -1026,6 +1026,18 @@ var solanaTraderPlugin = {
         onUnauthorized
       });
     };
+    const patch = async (apiPath, body) => {
+      const token = await sessionManager.getAccessToken();
+      return orchestratorRequest({
+        baseUrl: orchestratorUrl,
+        method: "PATCH",
+        path: apiPath,
+        body,
+        timeout: apiTimeout,
+        accessToken: token,
+        onUnauthorized
+      });
+    };
     const del = async (apiPath) => {
       const token = await sessionManager.getAccessToken();
       return orchestratorRequest({
@@ -1466,7 +1478,12 @@ var solanaTraderPlugin = {
             description: "Advisory only \u2014 server decides position mode internally. Sent for future compatibility."
           })
         ),
-        idempotencyKey: Type.Optional(Type.String({ description: "Unique key to prevent duplicate executions (e.g., UUID). Server uses walletId + key for replay cache." }))
+        idempotencyKey: Type.Optional(Type.String({ description: "Unique key to prevent duplicate executions (e.g., UUID). Server uses walletId + key for replay cache." })),
+        agentId: Type.Optional(
+          Type.String({
+            description: "Optional agent id for gateway-forwarded notices (e.g. main). If omitted, the plugin config `agentId` is sent when set so default-risk messages reach the right agent."
+          })
+        )
       }),
       execute: wrapExecute("solana_trade_execute", async (_id, params) => {
         const headers = {};
@@ -1481,6 +1498,8 @@ var solanaTraderPlugin = {
           slPct: params.slPct,
           managementMode: params.managementMode
         };
+        const execAgentId = typeof params.agentId === "string" && params.agentId.trim().length > 0 ? params.agentId.trim() : config.agentId && String(config.agentId).trim().length > 0 ? String(config.agentId).trim() : void 0;
+        if (execAgentId) body.agentId = execAgentId;
         const tsExecute = params.trailingStop;
         if (tsExecute?.levels && Array.isArray(tsExecute.levels) && tsExecute.levels.length > 0) {
           body.trailingStop = tsExecute;
@@ -1700,7 +1719,7 @@ var solanaTraderPlugin = {
     });
     api.registerTool({
       name: "solana_positions",
-      description: "List trading positions with mark-to-market. **PnL:** for Solana wallets, `realizedPnl` / `unrealizedPnl` are returned in SOL-native units. `unrealizedReturnPct` is ROI on cost basis (for sweep-dead-tokens logic).",
+      description: "List trading positions with mark-to-market. **PnL:** for Solana wallets, `realizedPnl` / `unrealizedPnl` are returned in SOL-native units. `unrealizedReturnPct` is ROI on cost basis (for sweep-dead-tokens logic). **Exit plan (source of truth):** use each position's `tpLevelsDetailed`, `slLevels`, `trailingStopPct`, `trailingStopLevels`, and `deadlockState.exits` \u2014 never guess exits from mode tables or memory.",
       parameters: Type.Object({
         status: Type.Optional(Type.String({ description: "Filter by status: 'open', 'closed', or omit for all" }))
       }),
@@ -1710,6 +1729,122 @@ var solanaTraderPlugin = {
         return get(reqPath);
       })
     });
+    api.registerTool({
+      name: "risk_management_get_default",
+      description: "Read per-wallet default exit parameters used when a buy is executed **without** any TP/SL/trailing fields. Returns either the user's saved defaults or the platform system default (`source`: user | system).",
+      parameters: Type.Object({}),
+      execute: wrapExecute(
+        "risk_management_get_default",
+        async () => get(`/api/wallet/risk-defaults?walletId=${walletId}`)
+      )
+    });
+    api.registerTool({
+      name: "trade_size_limit_get",
+      description: "Read the per-wallet maximum **buy** size in SOL enforced by the API (stored in `wallet.limits.maxTradeSizeSol`; platform default 1.5 SOL when unset). Always use this before sizing buys; never guess the limit.",
+      parameters: Type.Object({}),
+      execute: wrapExecute(
+        "trade_size_limit_get",
+        async () => get(`/api/wallet/max-trade-size?walletId=${walletId}`)
+      )
+    });
+    api.registerTool({
+      name: "trade_size_limit_set",
+      description: "Set the per-wallet maximum buy size in SOL (persisted on the wallet `limits` JSON). Subject to a platform ceiling.",
+      parameters: Type.Object({
+        maxTradeSizeSol: Type.Number({ exclusiveMinimum: 0 })
+      }),
+      execute: wrapExecute(
+        "trade_size_limit_set",
+        async (_id, params) => put("/api/wallet/max-trade-size", {
+          walletId,
+          maxTradeSizeSol: params.maxTradeSizeSol
+        })
+      )
+    });
+    api.registerTool({
+      name: "risk_management_set_default",
+      description: "Save per-wallet default exit parameters (`tpExits`, `slExits`, `trailingStop.levels`) applied on buys that omit risk fields. Same shape as trade execute exit payloads.",
+      parameters: Type.Object({
+        tpExits: Type.Array(
+          Type.Object({
+            percent: Type.Number(),
+            amountPct: Type.Number()
+          }),
+          { minItems: 1 }
+        ),
+        slExits: Type.Array(
+          Type.Object({
+            percent: Type.Number(),
+            amountPct: Type.Number()
+          }),
+          { minItems: 1 }
+        ),
+        trailingStop: Type.Object({
+          levels: Type.Array(
+            Type.Object({
+              percentage: Type.Number(),
+              amount: Type.Optional(Type.Number()),
+              triggerAboveATH: Type.Optional(Type.Number())
+            }),
+            { minItems: 1, maxItems: 5 }
+          )
+        })
+      }),
+      execute: wrapExecute(
+        "risk_management_set_default",
+        async (_id, params) => put("/api/wallet/risk-defaults", {
+          walletId,
+          tpExits: params.tpExits,
+          slExits: params.slExits,
+          trailingStop: params.trailingStop
+        })
+      )
+    });
+    api.registerTool({
+      name: "position_risk_management_update",
+      description: "Update **percentages and amounts only** on an open position's live exit plan (CaptureSell + stored position metadata). Cannot add or remove levels \u2014 array lengths must match the existing subscription. Use after entry when refining TP/SL/trailing numerics.",
+      parameters: Type.Object({
+        tokenAddress: Type.String({ description: "SPL mint for the open position" }),
+        tpExits: Type.Optional(
+          Type.Array(
+            Type.Object({
+              percent: Type.Number(),
+              amountPct: Type.Number()
+            })
+          )
+        ),
+        slExits: Type.Optional(
+          Type.Array(
+            Type.Object({
+              percent: Type.Number(),
+              amountPct: Type.Number()
+            })
+          )
+        ),
+        trailingStop: Type.Optional(
+          Type.Object({
+            levels: Type.Array(
+              Type.Object({
+                percentage: Type.Number(),
+                amount: Type.Optional(Type.Number()),
+                triggerAboveATH: Type.Optional(Type.Number())
+              }),
+              { minItems: 1, maxItems: 5 }
+            )
+          })
+        )
+      }),
+      execute: wrapExecute("position_risk_management_update", async (_id, params) => {
+        const body = {
+          walletId,
+          tokenAddress: params.tokenAddress
+        };
+        if (params.tpExits) body.tpExits = params.tpExits;
+        if (params.slExits) body.slExits = params.slExits;
+        if (params.trailingStop) body.trailingStop = params.trailingStop;
+        return patch("/api/position/risk-management", body);
+      })
+    });
     api.registerTool({
       name: "solana_wallet_token_balance",
       description: "Read on-chain SPL token balance (UI amount) for your trading wallet and a token mint. Same balance path as server exit monitoring (`balanceOf`).",

package/dist/src/http-client.js

@@ -1,6 +1,6 @@
 import {
   orchestratorRequest
-} from "../chunk-T4YWGIIR.js";
+} from "../chunk-VUIYNUGF.js";
 export {
   orchestratorRequest
 };

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "solana-traderclaw",
-  "version": "1.0.59",
+  "version": "1.0.60",
   "description": "TraderClaw V1-Upgraded — Solana trading for OpenClaw with intelligence lab, tool envelopes, prompt scrubbing, read-only X social intel, and split skill docs",
   "type": "module",
   "main": "./dist/index.js",

package/skills/solana-trader/SKILL.md

@@ -105,6 +105,8 @@ You operate in exactly one mode at a time. Default: `HARDENED`.
 
 ## Mode Parameters
 
+*The exit percentages in this table (e.g. suggested `slExits` / `tpExits` ranges) are **illustrative mode targets** for planning — they are **not** the live exit configuration of any open position.*
+
 | Parameter | HARDENED | DEGEN |
 |---|---|---|
 | Entry confidence threshold | High (strong confluence) | Moderate (lower bar) |
@@ -130,6 +132,17 @@ You operate in exactly one mode at a time. Default: `HARDENED`.
 - `trailingStop`: `{ levels: [{ percentage: <trailing drawdown %>, amount: <% of position to sell, default 100>, triggerAboveATH: <% above session ATH to arm, default 100 = 2× ATH> }] }` — 1–5 tiered trailing stops. Use `trailingStopPct` for simpler single-level trailing.
 - `slippageBps`: REQUIRED on both precheck and execute. Positive integer, basis points (e.g. 300 = 3%). Scale to liquidity, hard cap 800bps.
 
+## Source of truth for exit configuration (mandatory)
+
+- **Live** take-profit, stop-loss, and trailing-stop parameters for each **open** position come **only** from the orchestrator API via `solana_positions` (and related tools). Use the fields returned on each position row, especially: `tpLevelsDetailed`, `slLevels`, `trailingStopPct`, `trailingStopLevels`, and `deadlockState.exits` (including `trailingStopLevels` when present).
+- **Never** invent, recall from chat history, or copy numbers from the **Mode Parameters** table above as if they were your current exits.
+- If you need the **default** plan applied when a buy omitted risk fields, use `risk_management_get_default` (user override vs platform default). To change **defaults** for future buys, use `risk_management_set_default`. To adjust **numeric** TP/SL/trailing values on an **existing** position without adding or removing levels, use `position_risk_management_update`.
+
+## Maximum buy size in SOL (mandatory)
+
+- The API enforces a per-wallet cap on **buy** `sizeSol` via `wallet.limits.maxTradeSizeSol` stored in Supabase on the same `limits` JSON as other risk knobs (default **1.5 SOL** when the key is absent).
+- **Never** invent or recall a max size from mode tables or memory. Before proposing or executing a buy, call `trade_size_limit_get`. When the user wants a different cap, use `trade_size_limit_set` (subject to a platform ceiling).
+
 ## Position Execution Model (Authoritative)
 
 This section defines the UNIQUE valid interpretation of all exit-related parameters.

package/skills/solana-trader/workspace/TOOLS.md

@@ -13,7 +13,7 @@ Things like:
 - Rate limit observations
 - Anything environment-specific
 
-## Tool Inventory (98 tools — 95 Solana + 3 X read-only)
+## Tool Inventory (101 tools — 98 Solana + 3 X read-only)
 
 Every tool has a mandatory trigger — when the trigger condition is met, you MUST call the tool. "Cron-only" tools are called during cron jobs, not the heartbeat fast loop.
 
@@ -27,7 +27,7 @@ Every tool has a mandatory trigger — when the trigger condition is met, you MU
 | `solana_gateway_credentials_set` | Register gateway URL and token | When gateway is not registered (startup) |
 | `solana_gateway_forward_probe` | Test forwarding path health | Startup sequence; when events stop arriving |
 
-### Wallet & Capital (8)
+### Wallet & Capital (11)
 | Tool | Purpose | When to Call |
 |---|---|---|
 | `solana_wallets` | List all wallets | Startup; when user asks about wallets |
@@ -38,6 +38,11 @@ Every tool has a mandatory trigger — when the trigger condition is met, you MU
 | `solana_sweep_dead_tokens` | Batch-exit losing positions | `dead_money_sweep` cron; Step 0 when multiple dead positions found |
 | `solana_killswitch_status` | Check kill switch state | Step 0 every heartbeat |
 | `solana_killswitch` | Toggle kill switch (enabled + mode) | When consecutive loss limit hit; when user requests |
+| `risk_management_get_default` | Read per-wallet default TP/SL/trailing used when buys omit risk | Before relying on implicit defaults; after user asks about protection |
+| `risk_management_set_default` | Save per-wallet default exit plan for future buys | When user or policy wants custom defaults instead of platform system default |
+| `trade_size_limit_get` | Read max **buy** size (SOL) from wallet `limits` (default 1.5) | Before every buy or when user asks about size limits |
+| `trade_size_limit_set` | Set max **buy** size (SOL) on wallet `limits` | When user asks to change the per-order cap |
+| `position_risk_management_update` | Adjust TP/SL/trailing **numbers** on an open position (same level count) | After entry when refining exits without removing levels |
 
 ### Scanning & Discovery (4)
 | Tool | Purpose | When to Call |