@spfunctions/cli 1.1.0 → 1.1.3

package/dist/commands/agent.js

@@ -405,6 +405,7 @@ async function agentCommand(thesisId, opts) {
         { name: 'compact', description: 'Compress conversation history' },
         { name: 'new', description: 'Start fresh session' },
         { name: 'model', description: 'Switch model (e.g. /model anthropic/claude-sonnet-4)' },
+        { name: 'env', description: 'Show environment variable status' },
         { name: 'clear', description: 'Clear screen (keeps history)' },
         { name: 'exit', description: 'Exit agent (auto-saves)' },
     ], process.cwd());
@@ -451,6 +452,9 @@ async function agentCommand(thesisId, opts) {
         series: Type.Optional(Type.String({ description: 'Kalshi series ticker (e.g. KXWTIMAX)' })),
         market: Type.Optional(Type.String({ description: 'Specific market ticker' })),
     });
+    const webSearchParams = Type.Object({
+        query: Type.String({ description: 'Search keywords' }),
+    });
     const emptyParams = Type.Object({});
     const tools = [
         {
@@ -502,7 +506,7 @@ async function agentCommand(thesisId, opts) {
         {
             name: 'scan_markets',
             label: 'Scan Markets',
-            description: 'Search Kalshi prediction markets: by keywords, series ticker, or specific market ticker',
+            description: 'Search Kalshi prediction markets. Provide exactly one of: query (keyword search), series (series ticker), or market (specific ticker). If multiple are provided, priority is: market > series > query.',
             parameters: scanParams,
             execute: async (_toolCallId, params) => {
                 let result;
@@ -570,18 +574,102 @@ async function agentCommand(thesisId, opts) {
                 };
             },
         },
+        {
+            name: 'web_search',
+            label: 'Web Search',
+            description: 'Search latest news and information. Use for real-time info not yet covered by the causal tree or heartbeat engine.',
+            parameters: webSearchParams,
+            execute: async (_toolCallId, params) => {
+                const apiKey = process.env.TAVILY_API_KEY;
+                if (!apiKey) {
+                    return {
+                        content: [{ type: 'text', text: 'Tavily not configured. Set TAVILY_API_KEY to enable web search. You can also manually inject a signal and let the heartbeat engine search.' }],
+                        details: {},
+                    };
+                }
+                const res = await fetch('https://api.tavily.com/search', {
+                    method: 'POST',
+                    headers: { 'Content-Type': 'application/json' },
+                    body: JSON.stringify({
+                        api_key: apiKey,
+                        query: params.query,
+                        max_results: 5,
+                        search_depth: 'basic',
+                        include_answer: true,
+                    }),
+                });
+                if (!res.ok) {
+                    return {
+                        content: [{ type: 'text', text: `Search failed: ${res.status}` }],
+                        details: {},
+                    };
+                }
+                const data = await res.json();
+                const results = (data.results || []).map((r) => `[${r.title}](${r.url})\n${r.content?.slice(0, 200)}`).join('\n\n');
+                const answer = data.answer ? `Summary: ${data.answer}\n\n---\n\n` : '';
+                return {
+                    content: [{ type: 'text', text: `${answer}${results}` }],
+                    details: {},
+                };
+            },
+        },
     ];
-    // ── System prompt ──────────────────────────────────────────────────────────
-    const systemPrompt = `You are a SimpleFunctions prediction market trading assistant.
+    // ── System prompt builder ──────────────────────────────────────────────────
+    function buildSystemPrompt(ctx) {
+        const edgesSummary = ctx.edges
+            ?.sort((a, b) => Math.abs(b.edge) - Math.abs(a.edge))
+            .slice(0, 5)
+            .map((e) => `  ${(e.market || '').slice(0, 40)} | ${e.venue || 'kalshi'} | mkt ${e.marketPrice}\u00A2 \u2192 thesis ${e.thesisPrice}\u00A2 | edge ${e.edge > 0 ? '+' : ''}${e.edge} | ${e.orderbook?.liquidityScore || '?'}`)
+            .join('\n') || '  (no edge data)';
+        const nodesSummary = ctx.causalTree?.nodes
+            ?.filter((n) => n.depth === 0)
+            .map((n) => `  ${n.id} ${(n.label || '').slice(0, 40)} \u2014 ${Math.round(n.probability * 100)}%`)
+            .join('\n') || '  (no causal tree)';
+        const conf = typeof ctx.confidence === 'number'
+            ? Math.round(ctx.confidence * 100)
+            : (typeof ctx.confidence === 'string' ? parseInt(ctx.confidence) : 0);
+        return `You are a prediction market trading assistant. Your job is not to please the user \u2014 it is to help them see reality clearly and make correct trading decisions.
+
+## Your analytical framework
+
+Each thesis has a causal tree. Every node is a causal hypothesis with a probability. Nodes have causal relationships \u2014 when upstream nodes change, downstream nodes follow.
+
+Edge = thesis-implied price - actual market price. Positive edge means the market underprices this event. Negative edge means overpriced. Contracts with large edges AND good liquidity are the most tradeable.
+
+executableEdge is the real edge after subtracting the bid-ask spread. A contract with a big theoretical edge but wide spread may not be worth entering.
+
+Short-term markets (weekly/monthly contracts) settle into hard data that calibrates the long-term thesis. Don't use them to bet (outcomes are nearly known) \u2014 use them to verify whether causal tree node probabilities are accurate.
+
+## Your behavioral rules
+
+- Think before calling tools. If the data is already in context, don't re-fetch.
+- If the user asks about positions, check if Kalshi is configured first. If not, say so directly.
+- If the user says "note this" or mentions a news event, inject a signal. Don't ask "should I note this?"
+- If the user says "evaluate" or "run it", trigger immediately. Don't confirm.
+- Don't end every response with "anything else?" \u2014 the user will ask when they want to.
+- If the user asks about latest news or real-time events, use web_search first, then answer based on results. If you find important information, suggest injecting it as a signal.
+- If you notice an edge narrowing or disappearing, say so proactively. Don't only report good news.
+- If a causal tree node probability seriously contradicts the market price, point it out.
+- Use Chinese if the user writes in Chinese, English if they write in English.
+- For any question about prices, positions, or P&L, ALWAYS call a tool to get fresh data first. Never answer price-related questions using the cached data in this system prompt.
+- Align tables. Be precise with numbers to the cent.
 
-Current thesis: ${latestContext.thesis || latestContext.rawThesis || 'N/A'}
-Confidence: ${confidencePct}%
-Status: ${latestContext.status}
-Thesis ID: ${latestContext.thesisId || resolvedThesisId}
+## Current thesis state
 
-You have six tools available. Use them when you need real-time data. Answer directly when you don't.
-Be concise. Use Chinese if the user writes in Chinese, English if they write in English.
-Do NOT make up data. Always call tools to get current state.`;
+Thesis: ${ctx.thesis || ctx.rawThesis || 'N/A'}
+ID: ${ctx.thesisId || resolvedThesisId}
+Confidence: ${conf}%
+Status: ${ctx.status}
+
+Top-level causal tree nodes:
+${nodesSummary}
+
+Top 5 edges by magnitude:
+${edgesSummary}
+
+${ctx.lastEvaluation?.summary ? `Latest evaluation summary: ${ctx.lastEvaluation.summary.slice(0, 300)}` : ''}`;
+    }
+    const systemPrompt = buildSystemPrompt(latestContext);
     // ── Create Agent ───────────────────────────────────────────────────────────
     const agent = new Agent({
         initialState: {
@@ -741,6 +829,7 @@ Do NOT make up data. Always call tools to get current state.`;
                     C.emerald('/compact   ') + C.zinc400('Compress conversation history') + '\n' +
                     C.emerald('/new       ') + C.zinc400('Start fresh session') + '\n' +
                     C.emerald('/model <m> ') + C.zinc400('Switch model') + '\n' +
+                    C.emerald('/env       ') + C.zinc400('Show environment variable status') + '\n' +
                     C.emerald('/clear     ') + C.zinc400('Clear screen (keeps history)') + '\n' +
                     C.emerald('/exit      ') + C.zinc400('Exit (auto-saves)'));
                 addSpacer();
@@ -844,10 +933,14 @@ Do NOT make up data. Always call tools to get current state.`;
                     const newContext = await sfClient.getContext(newId);
                     resolvedThesisId = newContext.thesisId || newId;
                     latestContext = newContext;
-                    // Build new system prompt
+                    // Build new system prompt using the rich builder
+                    const newSysPrompt = buildSystemPrompt(newContext);
                     const newConf = typeof newContext.confidence === 'number'
                         ? Math.round(newContext.confidence * 100) : 0;
-                    const newSysPrompt = `You are a SimpleFunctions prediction market trading assistant.\n\nCurrent thesis: ${newContext.thesis || newContext.rawThesis || 'N/A'}\nConfidence: ${newConf}%\nStatus: ${newContext.status}\nThesis ID: ${resolvedThesisId}\n\nYou have six tools available. Use them when you need real-time data. Answer directly when you don't.\nBe concise. Use Chinese if the user writes in Chinese, English if they write in English.\nDo NOT make up data. Always call tools to get current state.`;
+                    // CRITICAL: Always clearMessages() first to reset agent internal state.
+                    // replaceMessages() on a mid-conversation agent corrupts pi-agent-core's
+                    // state machine, causing the TUI to freeze.
+                    agent.clearMessages();
                     // Load saved session or start fresh
                     const saved = loadSession(resolvedThesisId);
                     if (saved?.messages?.length > 0) {
@@ -856,7 +949,6 @@ Do NOT make up data. Always call tools to get current state.`;
                         addSystemText(C.emerald(`Switched to ${resolvedThesisId.slice(0, 8)}`) + C.zinc400(` (resumed ${saved.messages.length} messages)`));
                     }
                     else {
-                        agent.clearMessages();
                         agent.setSystemPrompt(newSysPrompt);
                         addSystemText(C.emerald(`Switched to ${resolvedThesisId.slice(0, 8)}`) + C.zinc400(' (new session)'));
                     }
@@ -873,42 +965,168 @@ Do NOT make up data. Always call tools to get current state.`;
                     addSystemText(C.red(`Switch failed: ${err.message}`));
                 }
                 addSpacer();
+                // Force re-focus editor so input stays responsive
+                tui.setFocus(editor);
                 tui.requestRender();
                 return true;
             }
             case '/compact': {
                 addSpacer();
-                const msgs = agent.state.messages;
-                if (msgs.length <= 10) {
-                    addSystemText(C.zinc400('Conversation too short to compact'));
-                    addSpacer();
-                    return true;
-                }
-                // Keep recent 6 messages (3 turns) + create summary of the rest
-                const recentCount = 6;
-                const toCompress = msgs.slice(0, -recentCount);
-                const toKeep = msgs.slice(-recentCount);
-                // Extract text for summary (no LLM, just bullet points)
-                const bulletPoints = [];
-                for (const m of toCompress) {
-                    const content = typeof m.content === 'string' ? m.content : '';
-                    if (m.role === 'user' && content) {
-                        bulletPoints.push(`- User: ${content.slice(0, 100)}`);
+                try {
+                    const msgs = agent.state.messages;
+                    if (msgs.length <= 10) {
+                        addSystemText(C.zinc400('Conversation too short to compact'));
+                        addSpacer();
+                        tui.setFocus(editor);
+                        return true;
+                    }
+                    // ── Find clean cut point ──────────────────────────────────────
+                    // Walk backwards counting user messages as turn starts.
+                    // Keep 3 complete turns. Never split a tool_call/tool_result pair.
+                    const turnsToKeep = 3;
+                    let turnsSeen = 0;
+                    let cutIndex = msgs.length;
+                    for (let i = msgs.length - 1; i >= 0; i--) {
+                        if (msgs[i].role === 'user') {
+                            turnsSeen++;
+                            if (turnsSeen >= turnsToKeep) {
+                                cutIndex = i;
+                                break;
+                            }
+                        }
                     }
-                    else if (m.role === 'assistant' && content) {
-                        bulletPoints.push(`- Assistant: ${content.slice(0, 150)}`);
+                    if (cutIndex <= 2) {
+                        addSystemText(C.zinc400('Not enough complete turns to compact'));
+                        addSpacer();
+                        tui.setFocus(editor);
+                        return true;
+                    }
+                    const toCompress = msgs.slice(0, cutIndex);
+                    const toKeep = msgs.slice(cutIndex);
+                    // ── Show loader ───────────────────────────────────────────────
+                    const compactLoader = new Loader(tui, (s) => C.emerald(s), (s) => C.zinc600(s), 'compacting with LLM...');
+                    compactLoader.start();
+                    chatContainer.addChild(compactLoader);
+                    tui.requestRender();
+                    // ── Serialize messages for the summarizer ─────────────────────
+                    // Strip tool results to raw text, cap total length to ~12k chars
+                    const serialized = [];
+                    let totalLen = 0;
+                    const MAX_CHARS = 12000;
+                    for (const m of toCompress) {
+                        if (totalLen >= MAX_CHARS)
+                            break;
+                        let text = '';
+                        if (typeof m.content === 'string') {
+                            text = m.content;
+                        }
+                        else if (Array.isArray(m.content)) {
+                            // OpenAI format: content blocks
+                            text = m.content
+                                .filter((b) => b.type === 'text')
+                                .map((b) => b.text)
+                                .join('\n');
+                        }
+                        if (!text)
+                            continue;
+                        const role = (m.role || 'unknown').toUpperCase();
+                        const truncated = text.slice(0, 800);
+                        const line = `[${role}]: ${truncated}`;
+                        serialized.push(line);
+                        totalLen += line.length;
                     }
+                    const conversationDump = serialized.join('\n\n');
+                    // ── Call OpenRouter for LLM summary ───────────────────────────
+                    // Use a cheap/fast model — gemini flash
+                    const summaryModel = 'google/gemini-2.0-flash-001';
+                    const summarySystemPrompt = `You are a conversation compressor. Given a conversation between a user and a prediction-market trading assistant, produce a dense summary that preserves:
+1. All factual conclusions, numbers, prices, and probabilities mentioned
+2. Key trading decisions, positions taken or discussed
+3. Signals injected, evaluations triggered, and their outcomes
+4. Any action items or pending questions
+
+Output a structured summary. Be concise but preserve every important detail — this summary replaces the original messages for continued conversation. Do NOT add commentary or meta-text. Just the summary.`;
+                    let summaryText;
+                    try {
+                        const orRes = await fetch('https://openrouter.ai/api/v1/chat/completions', {
+                            method: 'POST',
+                            headers: {
+                                'Content-Type': 'application/json',
+                                'Authorization': `Bearer ${openrouterKey}`,
+                                'HTTP-Referer': 'https://simplefunctions.com',
+                                'X-Title': 'SF Agent Compact',
+                            },
+                            body: JSON.stringify({
+                                model: summaryModel,
+                                messages: [
+                                    { role: 'system', content: summarySystemPrompt },
+                                    { role: 'user', content: `Summarize this conversation (${toCompress.length} messages):\n\n${conversationDump}` },
+                                ],
+                                max_tokens: 2000,
+                                temperature: 0.2,
+                            }),
+                        });
+                        if (!orRes.ok) {
+                            const errText = await orRes.text().catch(() => '');
+                            throw new Error(`OpenRouter ${orRes.status}: ${errText.slice(0, 200)}`);
+                        }
+                        const orData = await orRes.json();
+                        summaryText = orData.choices?.[0]?.message?.content || '';
+                        if (!summaryText) {
+                            throw new Error('Empty summary from LLM');
+                        }
+                    }
+                    catch (llmErr) {
+                        // LLM failed — fall back to bullet-point extraction
+                        const bulletPoints = [];
+                        for (const m of toCompress) {
+                            const content = typeof m.content === 'string' ? m.content : '';
+                            if (m.role === 'user' && content) {
+                                bulletPoints.push(`- User: ${content.slice(0, 100)}`);
+                            }
+                            else if (m.role === 'assistant' && content) {
+                                bulletPoints.push(`- Assistant: ${content.slice(0, 150)}`);
+                            }
+                        }
+                        summaryText = `[LLM summary failed: ${llmErr.message}. Fallback bullet points:]\n\n${bulletPoints.slice(-20).join('\n')}`;
+                    }
+                    // ── Remove loader ─────────────────────────────────────────────
+                    compactLoader.stop();
+                    chatContainer.removeChild(compactLoader);
+                    // ── Build compacted message array ──────────────────────────────
+                    // user(summary) → assistant(ack) → ...toKeep
+                    // This maintains valid user→assistant alternation.
+                    // toKeep starts with a user message (guaranteed by our cut logic).
+                    const compactedMessages = [
+                        {
+                            role: 'user',
+                            content: `[Conversation summary — ${toCompress.length} messages compressed]\n\n${summaryText}`,
+                        },
+                        {
+                            role: 'assistant',
+                            content: 'Understood. I have the full conversation context from the summary above. Continuing from where we left off.',
+                        },
+                        ...toKeep,
+                    ];
+                    // ── Replace agent state ───────────────────────────────────────
+                    // Clear first to reset internal state, then load compacted messages
+                    agent.clearMessages();
+                    agent.replaceMessages(compactedMessages);
+                    agent.setSystemPrompt(systemPrompt);
+                    persistSession();
+                    addSystemText(C.emerald(`Compacted: ${toCompress.length} messages \u2192 summary + ${toKeep.length} recent`) +
+                        C.zinc600(` (via ${summaryModel.split('/').pop()})`));
+                    addSpacer();
+                    // Force re-focus and render so editor stays responsive
+                    tui.setFocus(editor);
+                    tui.requestRender();
+                }
+                catch (err) {
+                    addSystemText(C.red(`Compact failed: ${err.message || err}`));
+                    addSpacer();
+                    tui.setFocus(editor);
+                    tui.requestRender();
                 }
-                const summary = bulletPoints.slice(-20).join('\n');
-                // Replace messages: summary + recent
-                const compactedMessages = [
-                    { role: 'assistant', content: `[Conversation summary - ${toCompress.length} messages compressed]\n${summary}` },
-                    ...toKeep,
-                ];
-                agent.replaceMessages(compactedMessages);
-                persistSession();
-                addSystemText(C.emerald(`Compacted: ${toCompress.length} messages \u2192 summary + ${toKeep.length} recent`));
-                addSpacer();
                 return true;
             }
             case '/new': {
@@ -922,6 +1140,33 @@ Do NOT make up data. Always call tools to get current state.`;
                 tui.requestRender();
                 return true;
             }
+            case '/env': {
+                addSpacer();
+                const envVars = [
+                    { name: 'SF_API_KEY', key: 'SF_API_KEY', required: true, mask: true },
+                    { name: 'SF_API_URL', key: 'SF_API_URL', required: false, mask: false },
+                    { name: 'OPENROUTER_KEY', key: 'OPENROUTER_API_KEY', required: true, mask: true },
+                    { name: 'KALSHI_KEY_ID', key: 'KALSHI_API_KEY_ID', required: false, mask: true },
+                    { name: 'KALSHI_PEM_PATH', key: 'KALSHI_PRIVATE_KEY_PATH', required: false, mask: false },
+                    { name: 'TAVILY_API_KEY', key: 'TAVILY_API_KEY', required: false, mask: true },
+                ];
+                const lines = envVars.map(v => {
+                    const val = process.env[v.key];
+                    if (val) {
+                        const display = v.mask
+                            ? val.slice(0, Math.min(8, val.length)) + '...' + val.slice(-4)
+                            : val;
+                        return `  ${v.name.padEnd(18)} ${C.emerald('\u2713')} ${C.zinc400(display)}`;
+                    }
+                    else {
+                        const note = v.required ? '\u5FC5\u987B' : '\u53EF\u9009';
+                        return `  ${v.name.padEnd(18)} ${C.red('\u2717')} ${C.zinc600(`\u672A\u914D\u7F6E\uFF08${note}\uFF09`)}`;
+                    }
+                });
+                addSystemText(C.zinc200(bold('Environment')) + '\n' + lines.join('\n'));
+                addSpacer();
+                return true;
+            }
             case '/clear': {
                 chatContainer.clear();
                 tui.requestRender();

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@spfunctions/cli",
-  "version": "1.1.0",
-  "description": "CLI for SimpleFunctions prediction market thesis agent",
+  "version": "1.1.3",
+  "description": "Prediction market intelligence CLI. Causal thesis model, 24/7 Kalshi/Polymarket scan, live orderbook, edge detection. Interactive agent mode with tool calling.",
   "bin": {
     "sf": "./dist/index.js"
   },
@@ -26,11 +26,15 @@
     "dist"
   ],
   "keywords": [
-    "prediction-markets",
-    "thesis-agent",
+    "prediction-market",
     "kalshi",
     "polymarket",
-    "cli"
+    "trading",
+    "cli",
+    "agent",
+    "orderbook",
+    "market-intelligence",
+    "edge-detection"
   ],
   "license": "MIT",
   "repository": {