@juspay/neurolink 8.9.0 → 8.10.0

package/CHANGELOG.md

@@ -1,3 +1,14 @@
+## [8.10.0](https://github.com/juspay/neurolink/compare/v8.9.0...v8.10.0) (2025-12-12)
+
+### Features
+
+- **(cli):** add video CLI flags tests and verification ([2d75347](https://github.com/juspay/neurolink/commit/2d753473cc75a219db4425783f4a062cca23873b))
+- **(models):** add GPT-5.2 and comprehensive model updates across all providers ([b75042f](https://github.com/juspay/neurolink/commit/b75042fcb98bbf19bdfe6f197ac12d6752b291ee))
+
+### Bug Fixes
+
+- **(ci):** use minimal plugins for semantic-release validation to avoid npm auth requirement ([f3ab09e](https://github.com/juspay/neurolink/commit/f3ab09e0cdc79ae70e55a37246d0edfe9a41a77d))
+
 ## [8.9.0](https://github.com/juspay/neurolink/compare/v8.8.0...v8.9.0) (2025-12-11)
 
 ### Features

package/dist/adapters/providerImageAdapter.js

@@ -21,6 +21,10 @@ export class MultimodalLogger {
  */
 const VISION_CAPABILITIES = {
     openai: [
+        // GPT-5.2 family (released Dec 11, 2025) - Latest flagship models
+        "gpt-5.2",
+        "gpt-5.2-chat-latest",
+        "gpt-5.2-pro",
         // GPT-5 family (released Aug 2025)
         "gpt-5",
         "gpt-5-2025-08-07",
@@ -34,6 +38,7 @@ const VISION_CAPABILITIES = {
         // o-series reasoning models (released Apr 2025)
         "o3",
         "o3-mini",
+        "o3-pro",
         "o4",
         "o4-mini",
         "o4-mini-deep-research",
@@ -48,12 +53,17 @@ const VISION_CAPABILITIES = {
         "gemini-3-pro-preview",
         "gemini-3-pro-preview-11-2025",
         "gemini-3-pro-latest",
+        "gemini-3-pro-image-preview",
         // Gemini 2.5 Series
         "gemini-2.5-pro",
         "gemini-2.5-flash",
+        "gemini-2.5-flash-lite",
+        "gemini-2.5-flash-image",
         // Gemini 2.0 Series
         "gemini-2.0-flash",
+        "gemini-2.0-flash-001",
         "gemini-2.0-flash-lite",
+        "gemini-2.0-flash-preview-image-generation",
         // Gemini 1.5 Series (Legacy)
         "gemini-1.5-pro",
         "gemini-1.5-flash",
@@ -67,24 +77,44 @@ const VISION_CAPABILITIES = {
         "claude-opus-4-5-20251101",
         "claude-haiku-4-5",
         "claude-haiku-4-5-20251001",
+        // Claude 4.1 and 4.0 Series
+        "claude-opus-4-1",
+        "claude-opus-4-1-20250805",
+        "claude-opus-4",
+        "claude-opus-4-20250514",
+        "claude-sonnet-4",
+        "claude-sonnet-4-20250514",
         // Claude 3.7 Series
         "claude-3-7-sonnet",
+        "claude-3-7-sonnet-20250219",
         // Claude 3.5 Series
         "claude-3-5-sonnet",
+        "claude-3-5-sonnet-20241022",
         // Claude 3 Series
         "claude-3-opus",
         "claude-3-sonnet",
         "claude-3-haiku",
     ],
     azure: [
+        // GPT-5.1 family (December 2025)
+        "gpt-5.1",
+        "gpt-5.1-chat",
+        "gpt-5.1-codex",
         // GPT-5 family
         "gpt-5",
         "gpt-5-pro",
+        "gpt-5-turbo",
+        "gpt-5-chat",
         "gpt-5-mini",
         // GPT-4.1 family
         "gpt-4.1",
         "gpt-4.1-mini",
         "gpt-4.1-nano",
+        // O-series
+        "o3",
+        "o3-mini",
+        "o3-pro",
+        "o4-mini",
         // Existing GPT-4
         "gpt-4o",
         "gpt-4o-mini",
@@ -97,10 +127,12 @@ const VISION_CAPABILITIES = {
         "gemini-3-pro-preview-11-2025",
         "gemini-3-pro-latest",
         "gemini-3-pro-preview",
+        "gemini-3-pro",
         // Gemini 2.5 models on Vertex AI
         "gemini-2.5-pro",
         "gemini-2.5-flash",
         "gemini-2.5-flash-lite",
+        "gemini-2.5-flash-image",
         // Gemini 2.0 models on Vertex AI
         "gemini-2.0-flash-001",
         "gemini-2.0-flash-lite",
@@ -146,27 +178,41 @@ const VISION_CAPABILITIES = {
     litellm: [
         // LiteLLM proxies to underlying providers
         // List models that support vision when going through the proxy
-        // Gemini models
-        "gemini-3-pro-preview",
-        "gemini-3-pro-latest",
-        "gemini-2.5-pro",
-        "gemini-2.5-flash",
-        "gemini-2.0-flash-lite",
-        // Claude 4.5 models
+        // OpenAI models via LiteLLM
+        "openai/gpt-5",
+        "openai/gpt-4o",
+        "openai/gpt-4o-mini",
+        "openai/gpt-4-turbo",
+        "gpt-5",
+        "gpt-4o",
+        "gpt-4.1",
+        // Anthropic models via LiteLLM
+        "anthropic/claude-sonnet-4-5-20250929",
+        "anthropic/claude-opus-4-1-20250805",
+        "anthropic/claude-3-5-sonnet-20240620",
         "claude-sonnet-4-5",
         "claude-sonnet-4-5-20250929",
         "claude-opus-4-5",
         "claude-opus-4-5-20251101",
         "claude-haiku-4-5-20251001",
-        // Claude 4 models
         "claude-sonnet-4",
         "claude-opus-4-1",
-        // OpenAI models
-        "gpt-4o",
-        "gpt-4.1",
-        "gpt-5",
+        // Gemini models via LiteLLM
+        "vertex_ai/gemini-2.5-pro",
+        "gemini/gemini-2.5-pro",
+        "gemini/gemini-2.0-flash",
+        "gemini-3-pro-preview",
+        "gemini-3-pro-latest",
+        "gemini-2.5-pro",
+        "gemini-2.5-flash",
+        "gemini-2.0-flash-lite",
+        // Groq models via LiteLLM (vision)
+        "groq/llama-3.2-11b-vision-preview",
     ],
     mistral: [
+        // Mistral Large (latest has vision via Pixtral integration)
+        "mistral-large-latest",
+        "mistral-large-2512",
         // Mistral Small 3.2 (vision support for images: PNG, JPEG, WEBP, GIF)
         "mistral-small",
         "mistral-small-latest",
@@ -176,26 +222,39 @@ const VISION_CAPABILITIES = {
         "mistral-medium",
         "mistral-medium-latest",
         "mistral-medium-3.1",
+        "mistral-medium-2508",
         // Magistral models (vision support)
         "magistral-small",
+        "magistral-small-latest",
         "magistral-medium",
+        "magistral-medium-latest",
         // Pixtral models (specialized vision models)
         "pixtral-12b",
         "pixtral-12b-latest",
         "pixtral-large",
         "pixtral-large-latest",
+        "pixtral-large-2502",
     ],
     ollama: [
         // Llama 4 family (May 2025 - Best vision + tool calling)
         "llama4:scout",
         "llama4:maverick",
-        // Llama 3.2 vision
+        "llama4:latest",
+        "llama4",
+        // Llama 3.2 vision variants
         "llama3.2-vision",
+        "llama3.2-vision:11b",
+        "llama3.2-vision:90b",
         // Gemma 3 family (SigLIP vision encoder - supports tool calling + vision)
+        "gemma3",
         "gemma3:4b",
         "gemma3:12b",
         "gemma3:27b",
         "gemma3:latest",
+        // Qwen 2.5 VL (Vision-Language)
+        "qwen2.5-vl",
+        "qwen2.5-vl:72b",
+        "qwen2.5-vl:32b",
         // Mistral Small family (vision + tool calling)
         "mistral-small3.1",
         "mistral-small3.1:large",
@@ -203,8 +262,24 @@ const VISION_CAPABILITIES = {
         "mistral-small3.1:small",
         // LLaVA (vision-focused)
         "llava",
+        "llava:7b",
+        "llava:13b",
+        "llava:34b",
+        "llava-llama3",
+        "llava-llama3:8b",
     ],
     bedrock: [
+        // Amazon Nova models (December 2024+) - multimodal vision support
+        "amazon.nova-premier",
+        "amazon.nova-premier-v1:0",
+        "amazon.nova-pro",
+        "amazon.nova-pro-v1:0",
+        "amazon.nova-lite",
+        "amazon.nova-lite-v1:0",
+        "amazon.nova-2-lite-v1:0",
+        "nova-premier",
+        "nova-pro",
+        "nova-lite",
         // Claude 4.5 family (supports vision, PDFs, images - September-November 2025)
         "claude-sonnet-4-5",
         "claude-sonnet-4.5",
@@ -213,7 +288,7 @@ const VISION_CAPABILITIES = {
         "claude-opus-4-5",
         "claude-opus-4.5",
         "anthropic.claude-opus-4-5",
-        "anthropic.claude-opus-4-5-20251101-v1:0",
+        "anthropic.claude-opus-4-5-20251124-v1:0",
         "claude-haiku-4-5",
         "claude-haiku-4.5",
         "anthropic.claude-haiku-4-5",
@@ -222,18 +297,22 @@ const VISION_CAPABILITIES = {
         "claude-sonnet-4",
         "claude-sonnet-4@",
         "anthropic.claude-sonnet-4",
+        "anthropic.claude-sonnet-4-20250514-v1:0",
         "claude-opus-4",
         "claude-opus-4-1",
         "claude-opus-4@",
         "anthropic.claude-opus-4",
+        "anthropic.claude-opus-4-1-20250805-v1:0",
         // Claude 3.7 Sonnet
         "claude-3-7-sonnet",
         "claude-3.7-sonnet",
         "anthropic.claude-3-7-sonnet",
+        "anthropic.claude-3-7-sonnet-20250219-v1:0",
         // Claude 3.5 Sonnet
         "claude-3-5-sonnet",
         "claude-3.5-sonnet",
         "anthropic.claude-3-5-sonnet",
+        "anthropic.claude-3-5-sonnet-20241022-v1:0",
         // Claude 3 Opus
         "claude-3-opus",
         "anthropic.claude-3-opus",
@@ -243,9 +322,32 @@ const VISION_CAPABILITIES = {
         // Claude 3 Haiku
         "claude-3-haiku",
         "anthropic.claude-3-haiku",
+        // Meta Llama 4 models (multimodal vision)
+        "meta.llama4-maverick-17b-instruct-v1:0",
+        "meta.llama4-scout-17b-instruct-v1:0",
+        // Meta Llama 3.2 vision models
+        "meta.llama3-2-90b-instruct-v1:0",
+        "meta.llama3-2-11b-instruct-v1:0",
+        // Mistral Pixtral (multimodal vision)
+        "mistral.pixtral-large-2502-v1:0",
         // Generic anthropic.claude prefix (catches all Claude models)
         "anthropic.claude",
     ],
+    huggingface: [
+        // Qwen 2.5 VL (Vision-Language)
+        "Qwen/Qwen2.5-VL-32B-Instruct",
+        "Qwen/Qwen2.5-VL-7B-Instruct",
+        // Microsoft Phi-3 Vision
+        "microsoft/Phi-3-vision-128k-instruct",
+        // LLaVA variants
+        "llava-hf/llava-1.5-7b-hf",
+        "llava-hf/llava-v1.6-mistral-7b-hf",
+    ],
+    sagemaker: [
+        // Meta Llama 4 vision models
+        "meta-llama-4-maverick-17b-128e-instruct",
+        "meta-llama-4-scout-17b-16e-instruct",
+    ],
 };
 /**
  * Provider Image Adapter - Smart routing and formatting
@@ -281,6 +383,21 @@ export class ProviderImageAdapter {
                 case "ollama":
                     adaptedPayload = this.formatForOpenAI(text, images);
                     break;
+                case "huggingface":
+                    adaptedPayload = this.formatForOpenAI(text, images);
+                    break;
+                case "sagemaker":
+                    adaptedPayload = this.formatForOpenAI(text, images);
+                    break;
+                case "litellm":
+                    adaptedPayload = this.formatForOpenAI(text, images);
+                    break;
+                case "mistral":
+                    adaptedPayload = this.formatForOpenAI(text, images);
+                    break;
+                case "bedrock":
+                    adaptedPayload = this.formatForAnthropic(text, images);
+                    break;
                 default:
                     throw new Error(`Vision not supported for provider: ${provider}`);
             }

package/dist/cli/factories/commandFactory.d.ts

@@ -9,6 +9,7 @@ export declare class CLICommandFactory {
     private static processCliCSVFiles;
     private static processCliPDFFiles;
     private static processCliFiles;
+    private static processCliVideoFiles;
     private static processOptions;
     private static handleOutput;
     /**

package/dist/cli/factories/commandFactory.js

@@ -60,6 +60,31 @@ export class CLICommandFactory {
             type: "string",
             description: "Add PDF file for analysis (can be used multiple times)",
         },
+        video: {
+            type: "string",
+            description: "Add video file for analysis (can be used multiple times) (MP4, WebM, MOV, AVI, MKV)",
+        },
+        "video-frames": {
+            type: "number",
+            default: 8,
+            description: "Number of frames to extract (default: 8)",
+        },
+        "video-quality": {
+            type: "number",
+            default: 85,
+            description: "Frame quality 0-100 (default: 85)",
+        },
+        "video-format": {
+            type: "string",
+            choices: ["jpeg", "png"],
+            default: "jpeg",
+            description: "Frame format (default: jpeg)",
+        },
+        "transcribe-audio": {
+            type: "boolean",
+            default: false,
+            description: "Extract and transcribe audio from video",
+        },
         file: {
             type: "string",
             description: "Add file with auto-detection (CSV, image, etc. - can be used multiple times)",
@@ -271,6 +296,13 @@ export class CLICommandFactory {
         }
         return Array.isArray(files) ? files : [files];
     }
+    // Helper method to process CLI video files
+    static processCliVideoFiles(videoFiles) {
+        if (!videoFiles) {
+            return undefined;
+        }
+        return Array.isArray(videoFiles) ? videoFiles : [videoFiles];
+    }
     // Helper method to process common options
     static processOptions(argv) {
         // Handle noColor option by disabling chalk
@@ -543,7 +575,8 @@ export class CLICommandFactory {
                     .example('$0 gen "Write a Python function" --provider openai', "Use specific provider")
                     .example('$0 generate "Code review" -m gpt-4 -t 0.3', "Use specific model and temperature")
                     .example('echo "Summarize this" | $0 generate', "Use stdin input")
-                    .example('$0 generate "Analyze data" --enable-analytics', "Enable usage analytics"));
+                    .example('$0 generate "Analyze data" --enable-analytics', "Enable usage analytics")
+                    .example('$0 generate "Describe this video" --video path/to/video.mp4', "Analyze video content"));
             },
             handler: async (argv) => await this.executeGenerate(argv),
         };
@@ -564,7 +597,8 @@ export class CLICommandFactory {
                     .example('$0 stream "Write a story about space"', "Stream a creative story")
                     .example('$0 stream "Explain machine learning" -p anthropic', "Stream with specific provider")
                     .example('$0 stream "Code walkthrough" --output story.txt', "Stream to file")
-                    .example('echo "Live demo" | $0 stream', "Stream from stdin"));
+                    .example('echo "Live demo" | $0 stream', "Stream from stdin")
+                    .example('$0 stream "Narrate this video" --video path/to/video.mp4', "Stream video analysis"));
             },
             handler: async (argv) => await this.executeStream(argv),
         };
@@ -1160,12 +1194,14 @@ export class CLICommandFactory {
             const imageBuffers = CLICommandFactory.processCliImages(argv.image);
             const csvFiles = CLICommandFactory.processCliCSVFiles(argv.csv);
             const pdfFiles = CLICommandFactory.processCliPDFFiles(argv.pdf);
+            const videoFiles = CLICommandFactory.processCliVideoFiles(argv.video);
             const files = CLICommandFactory.processCliFiles(argv.file);
             const generateInput = {
                 text: inputText,
                 ...(imageBuffers && { images: imageBuffers }),
                 ...(csvFiles && { csvFiles }),
                 ...(pdfFiles && { pdfFiles }),
+                ...(videoFiles && { videoFiles }),
                 ...(files && { files }),
             };
             const result = await sdk.generate({
@@ -1174,6 +1210,12 @@ export class CLICommandFactory {
                     maxRows: argv.csvMaxRows,
                     formatStyle: argv.csvFormat,
                 },
+                videoOptions: {
+                    frames: argv.videoFrames,
+                    quality: argv.videoQuality,
+                    format: argv.videoFormat,
+                    transcribeAudio: argv.transcribeAudio,
+                },
                 provider: enhancedOptions.provider,
                 model: enhancedOptions.model,
                 temperature: enhancedOptions.temperature,
@@ -1349,6 +1391,7 @@ export class CLICommandFactory {
         const imageBuffers = CLICommandFactory.processCliImages(argv.image);
         const csvFiles = CLICommandFactory.processCliCSVFiles(argv.csv);
         const pdfFiles = CLICommandFactory.processCliPDFFiles(argv.pdf);
+        const videoFiles = CLICommandFactory.processCliVideoFiles(argv.video);
         const files = CLICommandFactory.processCliFiles(argv.file);
         const stream = await sdk.stream({
             input: {
@@ -1356,12 +1399,19 @@ export class CLICommandFactory {
                 ...(imageBuffers && { images: imageBuffers }),
                 ...(csvFiles && { csvFiles }),
                 ...(pdfFiles && { pdfFiles }),
+                ...(videoFiles && { videoFiles }),
                 ...(files && { files }),
             },
             csvOptions: {
                 maxRows: argv.csvMaxRows,
                 formatStyle: argv.csvFormat,
             },
+            videoOptions: {
+                frames: argv.videoFrames,
+                quality: argv.videoQuality,
+                format: argv.videoFormat,
+                transcribeAudio: argv.transcribeAudio,
+            },
             provider: enhancedOptions.provider,
             model: enhancedOptions.model,
             temperature: enhancedOptions.temperature,