@qvac/sdk 0.13.5 → 0.14.1

package/dist/examples/llamacpp-cache.js

@@ -6,16 +6,16 @@ const systemPrompt = {
     content: "You are a concise travel assistant. Keep track of the user's preferences across turns.",
 };
 function printStats(stats) {
-    console.log("\nPerformance Stats:", {
+    console.log("\n▸ Performance Stats:", {
         timeToFirstToken: stats?.timeToFirstToken,
         tokensPerSecond: stats?.tokensPerSecond,
         cacheTokens: stats?.cacheTokens,
     });
 }
 async function runCachedCompletion(params) {
-    console.log(`\n=== ${params.label} ===`);
-    console.log(`Cache key: ${params.kvCache || "disabled"}`);
-    console.log("AI Response:");
+    console.log(`\n▸ ${params.label}`);
+    console.log(`▸ Cache key: ${params.kvCache || "disabled"}`);
+    console.log("▸ AI Response:");
     const result = completion({
         modelId: params.modelId,
         history: params.history,
@@ -33,18 +33,22 @@ async function runCachedCompletion(params) {
 }
 let modelId;
 try {
-    console.log("Loading llama.cpp model with cache support...");
+    console.log("▸ Loading llama.cpp model with cache support...");
     modelId = await loadModel({
         modelSrc: LLAMA_3_2_1B_INST_Q4_0,
         modelConfig: {
             ctx_size: 4096,
             verbosity: VERBOSITY.ERROR,
         },
-        onProgress: (progress) => {
-            console.log(`Loading: ${progress.percentage.toFixed(1)}%`);
+        onProgress: (p) => {
+            const mb = (n) => (n / 1e6).toFixed(1);
+            const line = `▸ Downloading ${p.percentage.toFixed(0)}% (${mb(p.downloaded)}/${mb(p.total)} MB)`;
+            process.stderr.write(process.stderr.isTTY ? `\r${line}` : `${line}\n`);
+            if (p.percentage >= 100)
+                process.stderr.write("\n");
         },
     });
-    console.log(`Model loaded successfully. Model ID: ${modelId}`);
+    console.log(`▸ Model loaded successfully. Model ID: ${modelId}`);
     await deleteCache({ kvCacheKey: sharedCacheKey });
     await deleteCache({ kvCacheKey: isolatedCacheKey });
     const firstUserMessage = {
@@ -83,10 +87,10 @@ try {
             },
         ],
     });
-    console.log("\nSummary:");
-    console.log(`- Reusing "${sharedCacheKey}" keeps conversation context across turns.`);
-    console.log(`- Switching to "${isolatedCacheKey}" starts a separate cache session.`);
-    console.log('- Use deleteCache({ kvCacheKey: "your-session" }) to clear a saved session.');
+    console.log("\n▸ Summary:");
+    console.log(`▸ - Reusing "${sharedCacheKey}" keeps conversation context across turns.`);
+    console.log(`▸ - Switching to "${isolatedCacheKey}" starts a separate cache session.`);
+    console.log('▸ - Use deleteCache({ kvCacheKey: "your-session" }) to clear a saved session.');
     await deleteCache({ kvCacheKey: sharedCacheKey });
     await deleteCache({ kvCacheKey: isolatedCacheKey });
     await unloadModel({ modelId, clearStorage: false });
@@ -98,9 +102,9 @@ catch (error) {
             await unloadModel({ modelId, clearStorage: false });
         }
         catch (cleanupError) {
-            console.warn("⚠️ cleanup failed:", cleanupError);
+            console.warn("✖ cleanup failed:", cleanupError);
         }
     }
-    console.error("❌ Error:", error);
+    console.error("✖", error);
     process.exit(1);
 }

package/dist/examples/llamacpp-dynamic-tools.js

@@ -76,7 +76,7 @@ async function chatTurn({ modelId, kvCache, history, tools }) {
     })();
     const toolEventsTask = (async () => {
         for await (const evt of result.toolCallStream) {
-            console.log(`\n→ tool call: ${evt.call.name}(${JSON.stringify(evt.call.arguments)})`);
+            console.log(`\n▸ tool call: ${evt.call.name}(${JSON.stringify(evt.call.arguments)})`);
         }
     })();
     await Promise.all([tokensTask, toolEventsTask]);
@@ -91,7 +91,7 @@ async function chatTurn({ modelId, kvCache, history, tools }) {
         if (schema) {
             const parsed = schema.safeParse(call.arguments);
             if (!parsed.success) {
-                console.warn(`   ✗ validation failed for ${call.name}:`, parsed.error);
+                console.log(`✖ validation failed for ${call.name}:`, parsed.error);
             }
         }
     }
@@ -110,9 +110,15 @@ async function main() {
             tools: true,
             toolsMode: "dynamic",
         },
-        onProgress: (progress) => console.log(`Loading: ${progress.percentage.toFixed(1)}%`),
+        onProgress: (p) => {
+            const mb = (n) => (n / 1e6).toFixed(1);
+            const line = `▸ Downloading ${p.percentage.toFixed(0)}% (${mb(p.downloaded)}/${mb(p.total)} MB)`;
+            process.stderr.write(process.stderr.isTTY ? `\r${line}` : `${line}\n`);
+            if (p.percentage >= 100)
+                process.stderr.write("\n");
+        },
     });
-    console.log(`✅ Model loaded: ${modelId}`);
+    console.log(`▸ Model loaded: ${modelId}`);
     const kvCache = `dynamic-tools-${Date.now()}`;
     const history = [
         {
@@ -123,7 +129,7 @@ async function main() {
     ];
     // Turn 1 — only weather tools available.
     history.push({ role: "user", content: "What's the weather in Tokyo?" });
-    console.log("\n🤖 Turn 1 (tools=weather):\n");
+    console.log("\n▸ Turn 1 (tools=weather):\n");
     await chatTurn({ modelId, kvCache, history, tools: weatherTools });
     // Turn 2 — same session, swap to horoscope tools. Dynamic mode lets the
     // model see a different tool set without invalidating the kv-cache.
@@ -131,16 +137,16 @@ async function main() {
         role: "user",
         content: "Now check my horoscope for Aquarius.",
     });
-    console.log("\n\n🤖 Turn 2 (tools=horoscope):\n");
+    console.log("\n\n▸ Turn 2 (tools=horoscope):\n");
     await chatTurn({ modelId, kvCache, history, tools: horoscopeTools });
     // Turn 3 — swap to a parameterless tool to confirm empty-arg flows work.
     history.push({ role: "user", content: "What's today's date?" });
-    console.log("\n\n🤖 Turn 3 (tools=date):\n");
+    console.log("\n\n▸ Turn 3 (tools=date):\n");
     await chatTurn({ modelId, kvCache, history, tools: dateTools });
-    console.log("\n\n🎉 Done.");
+    console.log("\n\n▸ Done.");
     await unloadModel({ modelId, clearStorage: false });
 }
 main().catch((err) => {
-    console.error("❌ Error:", err);
+    console.error("✖", err);
     process.exit(1);
 });

package/dist/examples/llamacpp-filesystem.js

@@ -2,11 +2,11 @@ import { completion, loadModel, unloadModel } from "@qvac/sdk";
 // Get GGUF file path from command line arguments
 const ggufPath = process.argv[2];
 if (!ggufPath) {
-    console.error("❌ Error: Please provide the path to a GGUF file as the first argument");
-    console.error("Usage: bun run examples/llamacpp-filesystem.ts <path-to-gguf-file>");
+    console.error("✖ Please provide the path to a GGUF file as the first argument");
+    console.error("✖ Usage: bun run examples/llamacpp-filesystem.ts <path-to-gguf-file>");
     process.exit(1);
 }
-console.log(`🚀 Loading GGUF model from: ${ggufPath}`);
+console.log(`▸ Loading GGUF model from: ${ggufPath}`);
 try {
     // Load model from provided file path
     const modelId = await loadModel({
@@ -15,14 +15,20 @@ try {
         modelConfig: {
             ctx_size: 4096,
         },
-        onProgress: (progress) => console.log(`Loading: ${progress.percentage.toFixed(1)}%`),
+        onProgress: (p) => {
+            const mb = (n) => (n / 1e6).toFixed(1);
+            const line = `▸ Downloading ${p.percentage.toFixed(0)}% (${mb(p.downloaded)}/${mb(p.total)} MB)`;
+            process.stderr.write(process.stderr.isTTY ? `\r${line}` : `${line}\n`);
+            if (p.percentage >= 100)
+                process.stderr.write("\n");
+        },
     });
-    console.log(`✅ Model loaded successfully! Model ID: ${modelId}`);
+    console.log(`▸ Model loaded successfully! Model ID: ${modelId}`);
     // Create conversation history
     const history = [
         { role: "user", content: "Explain Bitcoin in 3 key points" },
     ];
-    console.log("\n🤖 AI Response:");
+    console.log("\n▸ AI Response:");
     process.stdout.write(""); // Start response on new line
     // Stream completion
     const result = completion({ modelId, history, stream: true });
@@ -30,11 +36,11 @@ try {
         process.stdout.write(token);
     }
     const stats = await result.stats;
-    console.log("\n📊 Performance Stats:", stats);
-    console.log("\n\n🎉 Completed!");
+    console.log("\n▸ Performance Stats:", stats);
+    console.log("\n\n▸ Completed!");
     await unloadModel({ modelId, clearStorage: false });
 }
 catch (error) {
-    console.error("❌ Error:", error);
+    console.error("✖", error);
     process.exit(1);
 }

package/dist/examples/llamacpp-http.js

@@ -2,7 +2,7 @@ import { completion, loadModel, unloadModel } from "@qvac/sdk";
 // Get HTTP URL from command line arguments or use default HuggingFace URL
 const httpUrl = process.argv[2] ||
     "https://huggingface.co/bartowski/Llama-3.2-1B-Instruct-GGUF/resolve/main/Llama-3.2-1B-Instruct-Q4_0.gguf";
-console.log(`🚀 Loading GGUF model from HTTP: ${httpUrl}`);
+console.log(`▸ Loading GGUF model from HTTP: ${httpUrl}`);
 try {
     // Load model from HTTP URL
     const modelId = await loadModel({
@@ -11,18 +11,20 @@ try {
         modelConfig: {
             ctx_size: 4096,
         },
-        onProgress: (progress) => {
-            const downloadedMB = (progress.downloaded / 1024 / 1024).toFixed(2);
-            const totalMB = (progress.total / 1024 / 1024).toFixed(2);
-            console.log(`Loading: ${progress.percentage.toFixed(1)}% (${downloadedMB}MB / ${totalMB}MB)`);
+        onProgress: (p) => {
+            const mb = (n) => (n / 1e6).toFixed(1);
+            const line = `▸ Downloading ${p.percentage.toFixed(0)}% (${mb(p.downloaded)}/${mb(p.total)} MB)`;
+            process.stderr.write(process.stderr.isTTY ? `\r${line}` : `${line}\n`);
+            if (p.percentage >= 100)
+                process.stderr.write("\n");
         },
     });
-    console.log(`✅ Model loaded successfully! Model ID: ${modelId}`);
+    console.log(`▸ Model loaded successfully! Model ID: ${modelId}`);
     // Create conversation history
     const history = [
         { role: "user", content: "Explain quantum computing in 3 key points" },
     ];
-    console.log("\n🤖 AI Response:");
+    console.log("\n▸ AI Response:");
     process.stdout.write(""); // Start response on new line
     // Stream completion
     const result = completion({ modelId, history, stream: true });
@@ -30,11 +32,11 @@ try {
         process.stdout.write(token);
     }
     const stats = await result.stats;
-    console.log("\n📊 Performance Stats:", stats);
-    console.log("\n\n🎉 Completed!");
+    console.log("\n▸ Performance Stats:", stats);
+    console.log("\n\n▸ Completed!");
     await unloadModel({ modelId, clearStorage: false });
 }
 catch (error) {
-    console.error("❌ Error:", error);
+    console.error("✖", error);
     process.exit(1);
 }

package/dist/examples/llamacpp-multi-gpu.js

@@ -28,11 +28,11 @@ try {
         onProgress: (progress) => {
             if (progress.shardInfo) {
                 const { shardInfo } = progress;
-                console.log(`Downloading ${shardInfo.shardName} (${shardInfo.currentShard}/${shardInfo.totalShards}) ` +
+                console.log(`▸ Downloading ${shardInfo.shardName} (${shardInfo.currentShard}/${shardInfo.totalShards}) ` +
                     `— overall: ${shardInfo.overallPercentage.toFixed(1)}%`);
             }
             else {
-                console.log(`Downloading: ${progress.percentage.toFixed(1)}%`);
+                console.log(`▸ Downloading: ${progress.percentage.toFixed(1)}%`);
             }
         },
     });
@@ -47,11 +47,11 @@ try {
         process.stdout.write(token);
     }
     const stats = await result.stats;
-    console.log("\n\nStats:", stats);
+    console.log("\n\n▸ Stats:", stats);
     await unloadModel({ modelId, clearStorage: false });
     process.exit(0);
 }
 catch (error) {
-    console.error("Error:", error);
+    console.error("✖", error);
     process.exit(1);
 }

package/dist/examples/llamacpp-multimodal.js

@@ -1,6 +1,6 @@
 import { completion, loadModel, SMOLVLM2_500M_MULTIMODAL_Q8_0, MMPROJ_SMOLVLM2_500M_MULTIMODAL_Q8_0, unloadModel, } from "@qvac/sdk";
 if (process.argv.length < 3) {
-    console.error(`Specify an image file path as the first argument and a second image file path as the second (optional) argument`);
+    console.error(`▸ Specify an image file path as the first argument and a second image file path as the second (optional) argument`);
     process.exit(1);
 }
 try {
@@ -13,8 +13,12 @@ try {
             ctx_size: 1024,
             projectionModelSrc: MMPROJ_SMOLVLM2_500M_MULTIMODAL_Q8_0,
         },
-        onProgress: (progress) => {
-            console.log(`Loading: ${progress.percentage.toFixed(1)}%`);
+        onProgress: (p) => {
+            const mb = (n) => (n / 1e6).toFixed(1);
+            const line = `▸ Downloading ${p.percentage.toFixed(0)}% (${mb(p.downloaded)}/${mb(p.total)} MB)`;
+            process.stderr.write(process.stderr.isTTY ? `\r${line}` : `${line}\n`);
+            if (p.percentage >= 100)
+                process.stderr.write("\n");
         },
     });
     //Using one particular media
@@ -30,11 +34,11 @@ try {
         process.stdout.write(token);
     }
     const stats = await result.stats;
-    console.log("\n📊 Performance Stats:", stats);
-    console.log("--------------------------------");
+    console.log("\n▸ Performance Stats:", stats);
+    console.log("▸ --------------------------------");
     //Using multiple media
     if (process.argv.length < 4) {
-        console.log(`Only one image provided, terminating`);
+        console.log(`▸ Only one image provided, terminating`);
         process.exit(0);
     }
     const imageFilePath2 = process.argv[3];
@@ -50,11 +54,11 @@ try {
         process.stdout.write(token);
     }
     const stats2 = await result2.stats;
-    console.log("\n📊 Performance Stats:", stats2);
-    console.log("--------------------------------");
+    console.log("\n▸ Performance Stats:", stats2);
+    console.log("▸ --------------------------------");
     await unloadModel({ modelId, clearStorage: false });
 }
 catch (error) {
-    console.error("❌ Error:", error);
+    console.error("✖", error);
     process.exit(1);
 }

package/dist/examples/llamacpp-p2p.js

@@ -3,8 +3,12 @@ try {
     // First just cache the model
     await downloadAsset({
         assetSrc: LLAMA_3_2_1B_INST_Q4_0,
-        onProgress: (progress) => {
-            console.log(progress);
+        onProgress: (p) => {
+            const mb = (n) => (n / 1e6).toFixed(1);
+            const line = `▸ Downloading ${p.percentage.toFixed(0)}% (${mb(p.downloaded)}/${mb(p.total)} MB)`;
+            process.stderr.write(process.stderr.isTTY ? `\r${line}` : `${line}\n`);
+            if (p.percentage >= 100)
+                process.stderr.write("\n");
         },
     });
     // Then load it in memory from cache
@@ -27,11 +31,11 @@ try {
         process.stdout.write(token);
     }
     const stats = await result.stats;
-    console.log("\n📊 Performance Stats:", stats);
+    console.log("\n▸ Performance Stats:", stats);
     // Change `clearStorage: true` to delete cached model files
     await unloadModel({ modelId, clearStorage: false });
 }
 catch (error) {
-    console.error("❌ Error:", error);
+    console.error("✖", error);
     process.exit(1);
 }

package/dist/examples/llamacpp-sharded.js

@@ -20,13 +20,13 @@ try {
             if (progress.shardInfo) {
                 // For pattern-based or Hyperdrive shards
                 const { shardInfo } = progress;
-                console.log(`📥 Downloading ${shardInfo.shardName} (${shardInfo.currentShard}/${shardInfo.totalShards})\n` +
+                console.log(`▸ Downloading ${shardInfo.shardName} (${shardInfo.currentShard}/${shardInfo.totalShards})\n` +
                     `   File: ${progress.percentage.toFixed(1)}% (${(progress.downloaded / 1024 / 1024).toFixed(2)}MB / ${(progress.total / 1024 / 1024).toFixed(2)}MB)\n` +
                     `   Overall: ${shardInfo.overallPercentage.toFixed(1)}% (${(shardInfo.overallDownloaded / 1024 / 1024).toFixed(2)}MB / ${(shardInfo.overallTotal / 1024 / 1024).toFixed(2)}MB)`);
             }
             else {
                 // For archive-based shards
-                console.log(`📥 Progress: ${progress.percentage.toFixed(1)}% ` +
+                console.log(`▸ Progress: ${progress.percentage.toFixed(1)}% ` +
                     `(${(progress.downloaded / 1024 / 1024).toFixed(2)}MB / ${(progress.total / 1024 / 1024).toFixed(2)}MB)`);
             }
         },
@@ -38,16 +38,16 @@ try {
         },
     ];
     const result = completion({ modelId, history, stream: true });
-    console.log("\n🤖 Model response:");
+    console.log("\n▸ Model response:");
     for await (const token of result.tokenStream) {
         process.stdout.write(token);
     }
     const stats = await result.stats;
-    console.log("\n\n📊 Performance Stats:", stats);
+    console.log("\n\n▸ Performance Stats:", stats);
     await unloadModel({ modelId, clearStorage: false });
     process.exit(0);
 }
 catch (error) {
-    console.error("❌ Error:", error);
+    console.error("✖", error);
     process.exit(1);
 }

package/dist/examples/llamacpp-structured-output.js

@@ -58,25 +58,31 @@ async function runToContent(run) {
 try {
     const modelId = await loadModel({
         modelSrc: QWEN3_600M_INST_Q4,
-        onProgress: (p) => process.stdout.write(`\rLoading: ${p.percentage.toFixed(1)}%`),
+        onProgress: (p) => {
+            const mb = (n) => (n / 1e6).toFixed(1);
+            const line = `▸ Downloading ${p.percentage.toFixed(0)}% (${mb(p.downloaded)}/${mb(p.total)} MB)`;
+            process.stderr.write(process.stderr.isTTY ? `\r${line}` : `${line}\n`);
+            if (p.percentage >= 100)
+                process.stderr.write("\n");
+        },
     });
-    console.log(`\nModel loaded: ${modelId}\n`);
-    console.log("--- 1. responseFormat: text (baseline, free-form) ---");
+    console.log(`\n▸ Model loaded: ${modelId}\n`);
+    console.log("▸ --- 1. responseFormat: text (baseline, free-form) ---");
     await runToContent(completion({
         modelId,
         history: HISTORY,
         stream: true,
         responseFormat: { type: "text" },
     }));
-    console.log("\n--- 2. responseFormat: json_object (any valid JSON) ---");
+    console.log("\n▸ --- 2. responseFormat: json_object (any valid JSON) ---");
     const jsonObjectOut = await runToContent(completion({
         modelId,
         history: JSON_OBJECT_HISTORY,
         stream: true,
         responseFormat: { type: "json_object" },
     }));
-    console.log("parsed:", JSON.parse(jsonObjectOut.trim()));
-    console.log("\n--- 3. responseFormat: json_schema (strict shape) ---");
+    console.log("▸ parsed:", JSON.parse(jsonObjectOut.trim()));
+    console.log("\n▸ --- 3. responseFormat: json_schema (strict shape) ---");
     const jsonSchemaOut = await runToContent(completion({
         modelId,
         history: HISTORY,
@@ -92,14 +98,14 @@ try {
     // Output is guaranteed schema-valid JSON: object with exactly
     // {name: string, age: integer, occupation: string}, no extras.
     const parsed = JSON.parse(jsonSchemaOut.trim());
-    console.log("parsed:", parsed);
-    console.log("schema-valid:", typeof parsed.name === "string" &&
+    console.log("▸ parsed:", parsed);
+    console.log("▸ schema-valid:", typeof parsed.name === "string" &&
         Number.isInteger(parsed.age) &&
         typeof parsed.occupation === "string" &&
         Object.keys(parsed).sort().join(",") === "age,name,occupation");
     await unloadModel({ modelId });
 }
 catch (error) {
-    console.error("Error:", error);
+    console.error("✖", error);
     process.exit(1);
 }

package/dist/examples/logging-file-transport.js

@@ -47,10 +47,10 @@ try {
     await unloadModel({ modelId });
     logger.info("Model unloaded successfully");
     // Show user where logs were saved
-    console.log(`\n📄 All logs (including model internals) saved to: ${logFile}`);
-    console.log("You can inspect the file to see detailed model operation logs!");
+    console.log(`▸ Logs saved to ${logFile}`);
+    console.log("▸ Inspect it to see detailed model operation logs");
 }
 catch (error) {
-    console.error("❌ Error:", error);
+    console.error("✖", error);
     process.exit(1);
 }

package/dist/examples/logging-global.d.ts

@@ -0,0 +1,2 @@
+export {};
+//# sourceMappingURL=logging-global.d.ts.map

package/dist/examples/logging-global.js

@@ -0,0 +1,34 @@
+// loggerConsoleOutput: false in this config disables the default console
+// transport on both the client and the worker, so the only logs printed are
+// the ones our handler below receives.
+const configDir = import.meta.dirname ?? process.cwd();
+process.env["QVAC_CONFIG_PATH"] = `${configDir}/config/logging/logging.config.json`;
+const { loadModel, completion, unloadModel, subscribeServerLogs, LLAMA_3_2_1B_INST_Q4_0 } = await import("@qvac/sdk");
+try {
+    console.log("▸ Starting global logging demo...\n");
+    // One subscription captures every server-side log (SDK, models, RAG, …)
+    // without having to know any stream IDs ahead of time.
+    const unsubscribe = subscribeServerLogs((log) => {
+        console.log(`[SDK] [${log.level.toUpperCase()}] [${log.namespace}] ${log.message}`);
+    });
+    const modelId = await loadModel({
+        modelSrc: LLAMA_3_2_1B_INST_Q4_0,
+        modelConfig: { ctx_size: 2048 },
+    });
+    const result = completion({
+        modelId,
+        history: [{ role: "user", content: "Count from 1 to 5." }],
+        stream: true,
+    });
+    console.log("▸ Response:\n");
+    for await (const token of result.tokenStream) {
+        process.stdout.write(token);
+    }
+    await unloadModel({ modelId, clearStorage: false });
+    unsubscribe();
+}
+catch (error) {
+    console.error("✖", error);
+    process.exit(1);
+}
+export {};

package/dist/examples/logging-streaming.js

@@ -1,10 +1,10 @@
 import { loadModel, completion, unloadModel, loggingStream, SDK_LOG_ID, LLAMA_3_2_1B_INST_Q4_0, GTE_LARGE_FP16, VERBOSITY, embed, } from "@qvac/sdk";
 try {
-    console.log("🚀 Starting log streaming demo...\n");
+    console.log("▸ Streaming SDK and model logs");
     // Note: To configure logging (level and console output), use config file:
     // { "loggerLevel": "debug", "loggerConsoleOutput": false } in qvac.config.json/js/ts
     // Subscribe to SDK server logs in background
-    console.log("📡 Starting SDK server log stream...\n");
+    console.log("▸ Subscribing to SDK server logs");
     (async () => {
         for await (const log of loggingStream({ id: SDK_LOG_ID })) {
             console.log(`[SDK] [${log.level.toUpperCase()}] [${log.namespace}] ${log.message}`);
@@ -13,7 +13,7 @@ try {
         // Stream terminated - normal on shutdown
     });
     // Load models
-    console.log("📥 Loading models (watch SDK logs above)...\n");
+    console.log("▸ Loading models");
     const llmModelId = await loadModel({
         modelSrc: LLAMA_3_2_1B_INST_Q4_0,
         modelConfig: {
@@ -25,7 +25,7 @@ try {
     const embedModelId = await loadModel({
         modelSrc: GTE_LARGE_FP16,
     });
-    console.log("📡 Starting model-specific log streams...\n");
+    console.log("▸ Subscribing to model logs");
     (async () => {
         for await (const log of loggingStream({ id: llmModelId })) {
             const timestamp = new Date(log.timestamp).toISOString();
@@ -54,20 +54,17 @@ try {
         modelId: embedModelId,
         text: messages[0]?.content ?? "Hello, world!",
     });
-    console.log("📝 Response:\n");
+    console.log("▸ Response");
     for await (const token of result.tokenStream) {
         process.stdout.write(token);
     }
     console.log("Embedding (first 20 elements)", embedding.slice(0, 20));
     console.log("Embeddings length", embedding.length);
-    console.log("\n💡 Notice three log streams running:\n" +
-        "   - [SDK] = SDK server operations\n" +
-        "   - [LLM] = LLM model inference logs\n" +
-        "   - [EMBED] = Embedding model logs\n");
+    console.log("▸ Three streams running: [SDK] server, [LLM] inference, [EMBED] embedding");
     await unloadModel({ modelId: llmModelId, clearStorage: false });
     await unloadModel({ modelId: embedModelId, clearStorage: false });
 }
 catch (error) {
-    console.error("❌ Error:", error);
+    console.error("✖", error);
     process.exit(1);
 }