@qvac/sdk 0.13.5 → 0.14.1

package/dist/examples/mcp-websearch.js

@@ -45,11 +45,11 @@ function parseSearchResults(mcpResult) {
 }
 let mcpClient = null;
 try {
-    console.log("🦆 MCP DuckDuckGo Search Example\n");
+    console.log("▸ MCP DuckDuckGo Search Example\n");
     // ============================================================
     // STEP 1: Connect to DuckDuckGo MCP server
     // ============================================================
-    console.log("1️⃣  Starting DuckDuckGo MCP server...");
+    console.log("▸ Starting DuckDuckGo MCP server...");
     mcpClient = new Client({
         name: "qvac-ddg-example",
         version: "1.0.0",
@@ -59,20 +59,26 @@ try {
         args: ["-y", "@oevortex/ddg_search"],
     });
     await mcpClient.connect(transport);
-    console.log("   ✓ MCP server connected\n");
+    console.log("▸ MCP server connected\n");
     // ============================================================
     // STEP 2: Load model
     // ============================================================
-    console.log("2️⃣  Loading model...");
+    console.log("▸ Loading model...");
     const modelId = await loadModel({
         modelSrc: QWEN3_1_7B_INST_Q4,
         modelConfig: {
             ctx_size: 4096,
             tools: true,
         },
-        onProgress: (progress) => process.stdout.write(`\r   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(`\n   ✓ Model loaded\n`);
+    console.log(`\n▸ Model loaded\n`);
     // ============================================================
     // STEP 3: Ask AI to search the web (with MCP client)
     // ============================================================
@@ -88,8 +94,8 @@ Always cite your sources with the URL.`,
             content: "What is the current weather in New York City?",
         },
     ];
-    console.log("3️⃣  Asking AI to search the web...\n");
-    console.log("🤖 AI Response:");
+    console.log("▸ Asking AI to search the web...\n");
+    console.log("▸ AI Response:");
     // Pass MCP client directly to completion - tools are adapted internally!
     const result = completion({
         modelId,
@@ -106,19 +112,19 @@ Always cite your sources with the URL.`,
     // STEP 4: Execute tool calls using call() - automatic MCP routing!
     // ============================================================
     if (toolCalls.length > 0) {
-        console.log("4️⃣  Executing search...\n");
+        console.log("▸ Executing search...\n");
         const toolResults = [];
         for (const toolCall of toolCalls) {
-            console.log(`🔍 ${toolCall.name}(${JSON.stringify(toolCall.arguments)})`);
+            console.log(`▸ ${toolCall.name}(${JSON.stringify(toolCall.arguments)})`);
             if (!toolCall.invoke) {
-                console.log(`   ⚠️ No handler found for tool "${toolCall.name}"`);
+                console.log(`▸ No handler found for tool "${toolCall.name}"`);
                 continue;
             }
             // Use invoke() - automatically routes to the correct MCP client!
             const mcpResult = await toolCall.invoke();
             // Parse and clean up the search results
             const cleanResult = parseSearchResults(mcpResult);
-            console.log(`   ✓ Got search results:`);
+            console.log(`▸ Got search results:`);
             console.log(cleanResult
                 .split("\n")
                 .map((l) => `      ${l}`)
@@ -129,7 +135,7 @@ Always cite your sources with the URL.`,
         // ============================================================
         // STEP 5: Continue with search results
         // ============================================================
-        console.log("5️⃣  Getting AI response with search results...\n");
+        console.log("▸ Getting AI response with search results...\n");
         history.push({
             role: "assistant",
             content: await result.text,
@@ -140,7 +146,7 @@ Always cite your sources with the URL.`,
                 content: tr.result,
             });
         }
-        console.log("🤖 Final Response:");
+        console.log("▸ Final Response:");
         const finalResult = completion({
             modelId,
             history,
@@ -155,14 +161,14 @@ Always cite your sources with the URL.`,
     // ============================================================
     // Cleanup
     // ============================================================
-    console.log("6️⃣  Cleaning up...");
+    console.log("▸ Cleaning up...");
     await unloadModel({ modelId, clearStorage: false });
-    console.log("   ✓ Done\n");
-    console.log("🎉 Example completed!");
+    console.log("▸ Done\n");
+    console.log("▸ Example completed!");
     process.exit(0);
 }
 catch (error) {
-    console.error("❌ Error:", error);
+    console.error("✖", error);
     process.exit(1);
 }
 finally {

package/dist/examples/multi-model-demo.js

@@ -11,7 +11,13 @@ try {
         modelConfig: {
             ctx_size: 4096,
         },
-        onProgress: (progress) => console.log(`Loading Bob: ${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");
+        },
     });
     const aliceHistory = [
         {
@@ -26,7 +32,7 @@ try {
             content: "You ask questions about Bitcoin in one sentence.",
         },
     ];
-    console.log("🙋🏻‍♂️ Bob: ", "What is Bitcoin?");
+    console.log("Bob: ", "What is Bitcoin?");
     const aliceResponse = completion({
         modelId: alice,
         history: [...aliceHistory],
@@ -34,8 +40,8 @@ try {
     });
     const aliceText = await aliceResponse.text;
     aliceHistory.push({ role: "assistant", content: aliceText });
-    console.log("🙋🏻‍♀️ Alice: ", aliceText);
-    console.log("📊 Alice Stats: ", await aliceResponse.stats);
+    console.log("Alice: ", aliceText);
+    console.log("▸ Alice Stats: ", await aliceResponse.stats);
     const bobResponse = completion({
         modelId: bob,
         history: [...bobHistory, { role: "user", content: aliceText }],
@@ -43,8 +49,8 @@ try {
     });
     const bobText = await bobResponse.text;
     bobHistory.push({ role: "assistant", content: bobText });
-    console.log("🙋🏻‍♂️ Bob: ", bobText);
-    console.log("📊 Bob Stats: ", await bobResponse.stats);
+    console.log("Bob: ", bobText);
+    console.log("▸ Bob Stats: ", await bobResponse.stats);
     const aliceResponse2 = completion({
         modelId: alice,
         history: [...aliceHistory, { role: "user", content: bobText }],
@@ -52,8 +58,8 @@ try {
     });
     const aliceText2 = await aliceResponse2.text;
     aliceHistory.push({ role: "assistant", content: aliceText2 });
-    console.log("🙋🏻‍♀️ Alice: ", aliceText2);
-    console.log("📊 Alice Stats: ", await aliceResponse2.stats);
+    console.log("Alice: ", aliceText2);
+    console.log("▸ Alice Stats: ", await aliceResponse2.stats);
     const bobResponse2 = completion({
         modelId: bob,
         history: [...bobHistory, { role: "user", content: aliceText2 }],
@@ -61,12 +67,12 @@ try {
     });
     const bobText2 = await bobResponse2.text;
     bobHistory.push({ role: "assistant", content: bobText2 });
-    console.log("🙋🏻‍♂️ Bob: ", bobText2);
-    console.log("📊 Bob Stats: ", await bobResponse2.stats);
+    console.log("Bob: ", bobText2);
+    console.log("▸ Bob Stats: ", await bobResponse2.stats);
     await unloadModel({ modelId: alice, clearStorage: false });
     await unloadModel({ modelId: bob, clearStorage: false });
 }
 catch (error) {
-    console.error("❌ Error:", error);
+    console.error("✖", error);
     process.exit(1);
 }

package/dist/examples/ocr-fasttext.js

@@ -9,19 +9,17 @@
  * Pass a custom image path, or download the default image into examples/image/:
  *   https://github.com/tetherto/qvac/blob/main/packages/sdk/examples/image/basic_test.bmp
  */
-import { close, loadModel, ocr, OCR_LATIN_RECOGNIZER_1, unloadModel, } from "@qvac/sdk";
+import { close, loadModel, ocr, OCR_LATIN, unloadModel, } from "@qvac/sdk";
 import path from "path";
 import { fileURLToPath } from "url";
 const __dirname = path.dirname(fileURLToPath(import.meta.url));
 const imagePath = process.argv[2] || path.join(__dirname, "image/basic_test.bmp");
 try {
-    console.log("🚀 Loading OCR model...");
+    console.log("▸ Loading OCR model...");
     const modelId = await loadModel({
-        modelSrc: OCR_LATIN_RECOGNIZER_1,
+        modelSrc: OCR_LATIN,
         modelConfig: {
             langList: ["en"],
-            useGPU: true,
-            timeout: 30000,
             magRatio: 1.5,
             defaultRotationAngles: [90, 180, 270],
             contrastRetry: false,
@@ -29,8 +27,8 @@ try {
             recognizerBatchSize: 1,
         },
     });
-    console.log(`✅ Model loaded successfully! Model ID: ${modelId}`);
-    console.log(`\n🔍 Running OCR on: ${imagePath}`);
+    console.log(`▸ Model loaded successfully! Model ID: ${modelId}`);
+    console.log(`\n▸ Running OCR on: ${imagePath}`);
     const { blocks } = ocr({
         modelId,
         image: imagePath,
@@ -39,24 +37,24 @@ try {
         },
     });
     const result = await blocks;
-    console.log("\n📝 OCR Results:");
-    console.log("================================");
+    console.log("\n▸ OCR Results:");
+    console.log("▸ ================================");
     for (const block of result) {
-        console.log(`\n📄 Text: ${block.text}`);
+        console.log(block.text);
         if (block.bbox) {
-            console.log(`   📍 BBox: [${block.bbox.join(", ")}]`);
+            console.log(`▸ BBox: [${block.bbox.join(", ")}]`);
         }
         if (block.confidence !== undefined) {
-            console.log(`   ✓ Confidence: ${block.confidence}`);
+            console.log(`▸ Confidence: ${block.confidence}`);
         }
     }
-    console.log("\n================================");
-    console.log("\n🔄 Unloading model...");
+    console.log("\n▸ ================================");
+    console.log("\n▸ Unloading model...");
     await unloadModel({ modelId, clearStorage: false });
-    console.log("✅ Model unloaded successfully.");
+    console.log("▸ Model unloaded successfully.");
     process.exit(0);
 }
 catch (error) {
-    console.error("❌ Error during OCR processing:", error);
+    console.error("✖", error);
     await close();
 }

package/dist/examples/parallel-download.js

@@ -9,7 +9,7 @@ const assets = [
     { name: "GTE Large FP16", src: GTE_LARGE_FP16 },
 ];
 const timers = {};
-console.log(`\n=== Parallel Download (${assets.length} assets) ===\n`);
+console.log(`\n▸ Parallel Download (${assets.length} assets)\n`);
 const wallStart = now();
 try {
     const promises = assets.map((asset) => {
@@ -20,18 +20,18 @@ try {
                 const t = timers[asset.name];
                 if (t.firstProgress == null) {
                     t.firstProgress = now();
-                    console.log(`[${asset.name}] first progress at ${((t.firstProgress - wallStart) / 1000).toFixed(1)}s — ${progress.percentage}%`);
+                    console.log(`▸ [${asset.name}] first progress at ${((t.firstProgress - wallStart) / 1000).toFixed(1)}s — ${progress.percentage}%`);
                 }
                 if (progress.percentage === 100 && t.end == null) {
                     t.end = now();
-                    console.log(`[${asset.name}] done at ${((t.end - wallStart) / 1000).toFixed(1)}s`);
+                    console.log(`▸ [${asset.name}] done at ${((t.end - wallStart) / 1000).toFixed(1)}s`);
                 }
             },
         });
     });
     const results = await Promise.allSettled(promises);
     const wallEnd = now();
-    console.log(`\n=== Results ===\n`);
+    console.log(`\n▸ Results\n`);
     for (let i = 0; i < assets.length; i++) {
         const asset = assets[i];
         const result = results[i];
@@ -42,12 +42,12 @@ try {
             ? `${((t.firstProgress - t.start) / 1000).toFixed(1)}s`
             : "N/A";
         const total = t.end != null ? `${((t.end - t.start) / 1000).toFixed(1)}s` : "N/A";
-        console.log(`${status} ${asset.name}: first-progress=${timeToFirst}, total=${total}${reason}`);
+        console.log(`▸ ${status} ${asset.name}: first-progress=${timeToFirst}, total=${total}${reason}`);
     }
-    console.log(`\nWall time: ${((wallEnd - wallStart) / 1000).toFixed(1)}s`);
+    console.log(`\n▸ Wall time: ${((wallEnd - wallStart) / 1000).toFixed(1)}s`);
     void close();
 }
 catch (error) {
-    console.error("❌ Error:", error);
+    console.error("✖", error);
     process.exit(1);
 }

package/dist/examples/plugins.js

@@ -18,16 +18,16 @@ const configPath = `${configDir}/config/plugins/plugins.config.json`;
 const projectRoot = path.resolve(configDir, "..");
 const qvacOutputDir = path.join(projectRoot, "qvac");
 // ─── Generate the worker bundle from the plugins config ─────────────────────
-console.log(`🔍 Config: ${configPath}`);
-console.log(`⚠️  This example will generate a worker bundle in ${qvacOutputDir} and delete it on exit.`);
-console.log("   If you have an existing qvac/ folder with bundled files, they will be overwritten and removed.\n");
-console.log("🔨 Generating worker bundle from plugins config...\n");
+console.log(`▸ Config: ${configPath}`);
+console.log(`▸ This example will generate a worker bundle in ${qvacOutputDir} and delete it on exit.`);
+console.log("▸ If you have an existing qvac/ folder with bundled files, they will be overwritten and removed.\n");
+console.log("▸ Generating worker bundle from plugins config...\n");
 try {
     await bundleSdk({ projectRoot, configPath, quiet: true });
 }
 catch (error) {
-    console.error("❌ Failed to generate worker bundle.");
-    console.error("❌ Error:", error);
+    console.error("✖ Failed to generate worker bundle.");
+    console.error("✖", error);
     process.exit(1);
 }
 console.log("");
@@ -35,7 +35,7 @@ console.log("");
 function cleanup() {
     if (existsSync(qvacOutputDir)) {
         rmSync(qvacOutputDir, { recursive: true, force: true });
-        console.log(`\n🧹 Cleaned up ${qvacOutputDir}`);
+        console.log(`\n▸ Cleaned up ${qvacOutputDir}`);
     }
 }
 process.on("exit", cleanup);
@@ -43,34 +43,40 @@ process.on("exit", cleanup);
 // In a real app, place qvac.config.json (or .js/.ts) in your project root (auto-discovered).
 process.env["QVAC_CONFIG_PATH"] = configPath;
 const { completion, translate, embed, loadModel, unloadModel, LLAMA_3_2_1B_INST_Q4_0, BERGAMOT_EN_ES, GTE_LARGE_FP16, } = await import("@qvac/sdk");
-console.log("1. LLM Completion (llamacpp-completion plugin)");
+console.log("▸ 1. LLM Completion (llamacpp-completion plugin)");
 try {
     const llmModelId = await loadModel({
         modelSrc: LLAMA_3_2_1B_INST_Q4_0,
         modelConfig: { ctx_size: 2048 },
-        onProgress: (p) => console.log(`   Loading LLM: ${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(`   Model loaded: ${llmModelId}`);
+    console.log(`▸ Model loaded: ${llmModelId}`);
     const question = "What is 2 + 2? Answer in one word.";
-    console.log(`   Question: ${question}`);
+    console.log(`▸ Question: ${question}`);
     const result = completion({
         modelId: llmModelId,
         history: [{ role: "user", content: question }],
         stream: true,
     });
-    process.stdout.write("   Response: ");
+    console.log("▸ Response:");
     for await (const token of result.tokenStream) {
         process.stdout.write(token);
     }
-    console.log("\n");
+    console.log("");
     await unloadModel({ modelId: llmModelId });
-    console.log("   ✅ LLM unloaded\n");
+    console.log("▸ LLM unloaded\n");
 }
 catch (error) {
-    console.error("   ❌ LLM failed:", error);
+    console.error("✖ LLM failed:", error);
     process.exit(1);
 }
-console.log("2. Translation (nmtcpp-translation plugin)");
+console.log("▸ 2. Translation (nmtcpp-translation plugin)");
 try {
     const nmtModelId = await loadModel({
         modelSrc: BERGAMOT_EN_ES,
@@ -79,9 +85,15 @@ try {
             from: "en",
             to: "es",
         },
-        onProgress: (p) => console.log(`   Loading NMT: ${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(`   Model loaded: ${nmtModelId}`);
+    console.log(`▸ Model loaded: ${nmtModelId}`);
     const text = "Hello, how are you?";
     const result = translate({
         modelId: nmtModelId,
@@ -90,33 +102,33 @@ try {
         stream: false,
     });
     const translated = await result.text;
-    console.log(`   "${text}" -> "${translated}"\n`);
+    console.log(`"${text}" -> "${translated}"`);
     await unloadModel({ modelId: nmtModelId });
-    console.log("   ✅ NMT unloaded\n");
+    console.log("▸ NMT unloaded\n");
 }
 catch (error) {
-    console.error("   ❌ Translation failed:", error);
+    console.error("✖ Translation failed:", error);
     process.exit(1);
 }
-console.log("3. Embeddings (llamacpp-embedding plugin NOT in config)");
-console.log("   Attempting to load an embeddings model...\n");
+console.log("▸ 3. Embeddings (llamacpp-embedding plugin NOT in config)");
+console.log("▸ Attempting to load an embeddings model...\n");
 try {
     const embedModelId = await loadModel({
         modelSrc: GTE_LARGE_FP16,
     });
     await embed({ modelId: embedModelId, text: "test" });
-    console.error("   ❌ Unexpected: embed succeeded without the plugin!");
+    console.error("✖ Unexpected: embed succeeded without the plugin!");
     process.exit(1);
 }
 catch (error) {
     const message = error instanceof Error ? error.message : String(error);
     if (message.includes("Plugin not found")) {
-        console.log("   ✅ Expected PLUGIN_NOT_FOUND error:");
-        console.log(`   ${message}\n`);
+        console.log("▸ Expected PLUGIN_NOT_FOUND error:");
+        console.log(`▸ ${message}\n`);
     }
     else {
-        console.error("   ❌ Unexpected error:", error);
+        console.error("✖ Unexpected error:", error);
         process.exit(1);
     }
 }
-console.log("Done! Only the selected plugins were available.");
+console.log("▸ Done! Only the selected plugins were available.");

package/dist/examples/profiling/basic.js

@@ -5,13 +5,19 @@ try {
         mode: "verbose",
         includeServerBreakdown: true,
     });
-    console.log("Profiler enabled:", profiler.isEnabled());
+    console.log("▸ Profiler enabled:", profiler.isEnabled());
     const modelId = await loadModel({
         modelSrc: LLAMA_3_2_1B_INST_Q4_0,
-        onProgress: (p) => console.log(`  ${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("Model loaded:", modelId);
-    console.log("\n→ Running completion...");
+    console.log("▸ Model loaded:", modelId);
+    console.log("\n▸ Running completion...");
     const result = completion({
         modelId,
         history: [{ role: "user", content: "Say hello in one sentence." }],
@@ -23,12 +29,12 @@ try {
     console.log();
     await unloadModel({ modelId });
     // Export profiling data
-    console.log("\n=== Profiler Summary ===");
+    console.log("\n▸ Profiler Summary");
     console.log(profiler.exportSummary());
-    console.log("\n=== Profiler Table ===");
+    console.log("\n▸ Profiler Table");
     console.log(profiler.exportTable());
     const json = profiler.exportJSON();
-    console.log("\n=== Load Model Metrics ===");
+    console.log("\n▸ Load Model Metrics");
     // Filter for operation-level event (kind: "handler"), not RPC phase events
     const loadModelEvent = json.recentEvents?.find((e) => e.op === "loadModel" && e.kind === "handler");
     if (loadModelEvent) {
@@ -58,15 +64,15 @@ try {
         ];
         console.log("  Available ops:", ops.join(", "));
     }
-    console.log("\n=== Profiler JSON (structure) ===");
+    console.log("\n▸ Profiler JSON (structure)");
     console.log("  aggregates:", Object.keys(json.aggregates).length, "metrics");
     console.log("  recentEvents:", json.recentEvents?.length ?? 0, "events");
     console.log("  config:", json.config);
     // Disable profiling
     profiler.disable();
-    console.log("\nProfiler disabled:", !profiler.isEnabled());
+    console.log("\n▸ Profiler disabled:", !profiler.isEnabled());
 }
 catch (error) {
-    console.error("Error:", error);
+    console.error("✖", error);
     process.exit(1);
 }

package/dist/examples/profiling/per-call.js

@@ -1,29 +1,35 @@
 import { embed, loadModel, unloadModel, GTE_LARGE_FP16, profiler, } from "@qvac/sdk";
 try {
     profiler.disable();
-    console.log("Profiler globally enabled:", profiler.isEnabled());
+    console.log("▸ Profiler globally enabled:", profiler.isEnabled());
     const modelId = await loadModel({
         modelSrc: GTE_LARGE_FP16,
-        onProgress: (p) => console.log(`  ${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("Model loaded:", modelId);
-    console.log("\n=== Embed with per-call profiling ===");
+    console.log("▸ Model loaded:", modelId);
+    console.log("\n▸ Embed with per-call profiling");
     const { embedding: embedding1 } = await embed({ modelId, text: "Profile this specific call" }, { profiling: { enabled: true, includeServerBreakdown: true } });
-    console.log("Embedding dimensions:", embedding1.length);
-    console.log("\n=== Embed without profiling ===");
+    console.log("▸ Embedding dimensions:", embedding1.length);
+    console.log("\n▸ Embed without profiling");
     const { embedding: embedding2 } = await embed({
         modelId,
         text: "This call is not profiled",
     });
-    console.log("Embedding dimensions:", embedding2.length);
-    console.log("\n=== Embed with profiling explicitly disabled ===");
+    console.log("▸ Embedding dimensions:", embedding2.length);
+    console.log("\n▸ Embed with profiling explicitly disabled");
     const { embedding: embedding3 } = await embed({ modelId, text: "Profiling explicitly disabled for this call" }, { profiling: { enabled: false } });
-    console.log("Embedding dimensions:", embedding3.length);
+    console.log("▸ Embedding dimensions:", embedding3.length);
     await unloadModel({ modelId });
-    console.log("\n=== Profiler Summary (per-call data only) ===");
+    console.log("\n▸ Profiler Summary (per-call data only)");
     console.log(profiler.exportSummary());
 }
 catch (error) {
-    console.error("Error:", error);
+    console.error("✖", error);
     process.exit(1);
 }

package/dist/examples/quickstart.bare.d.ts

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

package/dist/examples/quickstart.bare.js

@@ -0,0 +1,18 @@
+// The Bare quickstart. Bare has no `process` global and does not spawn a worker,
+// so two setup steps come first: install bare-process as the `process` global,
+// then register the plugins this example uses via `plugins([...])`.
+import bareProcess from "bare-process";
+import { plugins, LLAMA_3_2_1B_INST_Q4_0 } from "@qvac/sdk";
+import { llmPlugin } from "@qvac/sdk/llamacpp-completion/plugin.js";
+globalThis.process = bareProcess;
+const { loadModel, completion, unloadModel } = plugins([llmPlugin]);
+// From here it is the same as the Node quickstart.
+const modelId = await loadModel({ modelSrc: LLAMA_3_2_1B_INST_Q4_0 });
+const history = [
+    { role: "user", content: "Explain quantum computing in one sentence" },
+];
+const result = completion({ modelId, history, stream: true });
+for await (const token of result.tokenStream) {
+    process.stdout.write(token);
+}
+await unloadModel({ modelId, autoClose: true });

package/dist/examples/quickstart.js

@@ -1,10 +1,17 @@
+// The SDK prints no logs by default. To see its client and server logs, run with
+// QVAC_CONFIG_PATH pointing at a config that sets "loggerConsoleOutput": true
+// (see the Quickstart docs).
 import { loadModel, LLAMA_3_2_1B_INST_Q4_0, completion, unloadModel, } from "@qvac/sdk";
 try {
     // Load a model into memory
     const modelId = await loadModel({
         modelSrc: 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");
         },
     });
     // You can use the loaded model multiple times
@@ -22,6 +29,6 @@ try {
     await unloadModel({ modelId });
 }
 catch (error) {
-    console.error("❌ Error:", error);
+    console.error("✖", error);
     process.exit(1);
 }