@juspay/neurolink 9.70.0 → 9.70.1

package/dist/utils/tokenLimits.js

@@ -76,6 +76,61 @@ export function getSafeMaxTokens(provider, model, requestedMaxTokens) {
     // Use the requested value if it's within limits
     return requestedMaxTokens;
 }
+/**
+ * Maximum output tokens supported by a given Anthropic Claude model.
+ *
+ * The native Vertex+Claude and native Anthropic message paths send `max_tokens`
+ * straight to the Anthropic API, which returns 400 if the value exceeds the
+ * model's published output ceiling. (The AI-SDK path clamps automatically;
+ * these native paths do not.) This table lets those paths default to the
+ * model's real ceiling — 64K for Sonnet/Haiku 4.x, 32K for Opus 4.x — instead of
+ * the legacy 4096 that silently truncated large structured responses.
+ *
+ * Unknown identifiers fall back to a safe modern floor (8192).
+ */
+export function getClaudeMaxOutputTokens(model) {
+    const m = (model ?? "").toLowerCase();
+    // Claude 4.x family: Opus 4.x = 32K, Sonnet/Haiku 4.x = 64K.
+    if (/opus[-_.]?4/.test(m)) {
+        return 32000;
+    }
+    if (/sonnet[-_.]?4/.test(m) || /haiku[-_.]?4/.test(m)) {
+        return 64000;
+    }
+    // Claude 3.7 Sonnet supports 64K output.
+    if (/3[-_.]?7[-_.]?sonnet/.test(m)) {
+        return 64000;
+    }
+    // Claude 3.5 Sonnet / Haiku → 8192.
+    if (/3[-_.]?5[-_.]?(sonnet|haiku)/.test(m)) {
+        return 8192;
+    }
+    // Claude 3 Opus / Sonnet / Haiku → 4096.
+    if (/claude-3-(opus|sonnet|haiku)/.test(m) || /3[-_.]?opus/.test(m)) {
+        return 4096;
+    }
+    // Bare family aliases (latest of a family) → assume the modern ceiling.
+    if (m.includes("opus")) {
+        return 32000;
+    }
+    if (m.includes("sonnet") || m.includes("haiku")) {
+        return 64000;
+    }
+    return 8192;
+}
+/**
+ * Resolve the `max_tokens` to send on a native Anthropic/Claude request: honour
+ * the caller's value but clamp it to the model's published ceiling, and default
+ * to that ceiling when the caller did not specify one. Prevents both silent
+ * truncation (the legacy 4096 default) and 400s from over-large requests.
+ */
+export function resolveClaudeMaxTokens(model, requested) {
+    const ceiling = getClaudeMaxOutputTokens(model);
+    if (requested !== undefined && requested !== null && requested > 0) {
+        return Math.min(requested, ceiling);
+    }
+    return ceiling;
+}
 /**
  * Validate if maxTokens is safe for a provider/model combination
  */

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@juspay/neurolink",
-  "version": "9.70.0",
+  "version": "9.70.1",
   "packageManager": "pnpm@10.15.1",
   "description": "Universal AI Development Platform with working MCP integration, multi-provider support, voice (TTS/STT/realtime), and professional CLI. 58+ external MCP servers discoverable, multimodal file processing, RAG pipelines. Build, test, and deploy AI applications with 21+ providers: OpenAI, Anthropic, Google AI Studio, Google Vertex, AWS Bedrock, Azure OpenAI, Mistral, LiteLLM, SageMaker, Hugging Face, Ollama, OpenAI-compatible, OpenRouter, DeepSeek, NVIDIA NIM, LM Studio, llama.cpp, plus voice (OpenAI TTS, ElevenLabs, Deepgram, Azure Speech).",
   "author": {
@@ -108,6 +108,8 @@
     "test:dynamic": "npx tsx test/continuous-test-suite-dynamic.ts",
     "test:proxy": "npx tsx test/continuous-test-suite-proxy.ts",
     "test:bugfixes": "npx tsx test/continuous-test-suite-bugfixes.ts",
+    "test:json": "npx tsx test/continuous-test-suite-json.ts",
+    "test:json-e2e": "npx tsx test/continuous-test-suite-json-e2e.ts",
     "test:workflow": "npx tsx test/continuous-test-suite-workflow.ts",
     "test:hitl": "npx tsx test/continuous-test-suite-hitl.ts",
     "test:tasks": "npx tsx test/continuous-test-suite-tasks.ts",
@@ -341,6 +343,7 @@
     "inquirer": "^13.3.0",
     "jose": "^6.1.3",
     "json-schema-to-zod": "^2.7.0",
+    "jsonrepair": "^3.14.0",
     "nanoid": "^5.1.5",
     "open": "^11.0.0",
     "ora": "^9.3.0",