bedrock-wrapper 2.4.3 → 2.4.5

package/CHANGELOG.md

@@ -1,6 +1,32 @@
 # Changelog
 All notable changes to this project will be documented in this file.
 
+## [2.4.5] - 2025-08-06 (GPT-OSS Models)
+### Added
+- Support for OpenAI GPT-OSS models on AWS Bedrock
+  - GPT-OSS-120B (120B parameter open weight model)
+  - GPT-OSS-20B (20B parameter open weight model)
+  - GPT-OSS-120B-Thinking (with reasoning tag preservation)
+  - GPT-OSS-20B-Thinking (with reasoning tag preservation)
+- `<reasoning>` tag processing for GPT-OSS thinking variants
+  - Regular GPT-OSS models automatically strip `<reasoning>` tags
+  - Thinking variants preserve `<reasoning>` tags (similar to Claude's `<think>` tags)
+- Non-streaming support for GPT-OSS models (streaming not supported by AWS Bedrock)
+- OpenAI-compatible API format with `max_completion_tokens` parameter
+
+### Technical Details
+- **Model Configuration**: All GPT-OSS models use standard messages API format
+- **API Compatibility**: Supports OpenAI-style requests with Apache 2.0 licensed models
+- **Response Processing**: Automatic reasoning tag handling based on model variant
+- **Streaming Fallback**: Automatic detection and fallback to non-streaming for unsupported models
+- **Testing Coverage**: Full integration with existing test suites and interactive example
+
+## [2.4.4] - 2025-08-05 (Claude 4.1 Opus)
+### Added
+- Support for Claude 4.1 Opus models
+  - Claude-4-1-Opus
+  - Claude-4-1-Opus-Thinking
+
 ## [2.4.3] - 2025-07-31 (Stop Sequences Fixes)
 ### Fixed
 - **Critical Discovery**: Removed stop sequences support from Llama models

package/README.md

@@ -104,19 +104,25 @@ Bedrock Wrapper is an npm package that simplifies the integration of existing Op
 
 | modelName                  | AWS Model Id                                 | Image |
 |----------------------------|----------------------------------------------|-------|
-| Claude-4-Opus              | us.anthropic.claude-opus-4-20250514-v1:0    |  ✅  |
-| Claude-4-Opus-Thinking     | us.anthropic.claude-opus-4-20250514-v1:0    |  ✅  |
-| Claude-4-Sonnet            | us.anthropic.claude-sonnet-4-20250514-v1:0  |  ✅  |
-| Claude-4-Sonnet-Thinking   | us.anthropic.claude-sonnet-4-20250514-v1:0  |  ✅  |
+| Claude-4-1-Opus            | us.anthropic.claude-opus-4-1-20250805-v1:0   |  ✅  |
+| Claude-4-1-Opus-Thinking   | us.anthropic.claude-opus-4-1-20250805-v1:0   |  ✅  |
+| Claude-4-Opus              | us.anthropic.claude-opus-4-20250514-v1:0     |  ✅  |
+| Claude-4-Opus-Thinking     | us.anthropic.claude-opus-4-20250514-v1:0     |  ✅  |
+| Claude-4-Sonnet            | us.anthropic.claude-sonnet-4-20250514-v1:0   |  ✅  |
+| Claude-4-Sonnet-Thinking   | us.anthropic.claude-sonnet-4-20250514-v1:0   |  ✅  |
 | Claude-3-7-Sonnet-Thinking | us.anthropic.claude-3-7-sonnet-20250219-v1:0 |  ✅  |
 | Claude-3-7-Sonnet          | us.anthropic.claude-3-7-sonnet-20250219-v1:0 |  ✅  |
 | Claude-3-5-Sonnet-v2       | anthropic.claude-3-5-sonnet-20241022-v2:0    |  ✅  |
 | Claude-3-5-Sonnet          | anthropic.claude-3-5-sonnet-20240620-v1:0    |  ✅  |
 | Claude-3-5-Haiku           | anthropic.claude-3-5-haiku-20241022-v1:0     |  ❌  |
 | Claude-3-Haiku             | anthropic.claude-3-haiku-20240307-v1:0       |  ✅  |
-| Nova-Pro                   | us.amazon.nova-pro-v1:0                     |  ✅  |
-| Nova-Lite                  | us.amazon.nova-lite-v1:0                    |  ✅  |
-| Nova-Micro                 | us.amazon.nova-micro-v1:0                   |  ❌  |
+| Nova-Pro                   | us.amazon.nova-pro-v1:0                      |  ✅  |
+| Nova-Lite                  | us.amazon.nova-lite-v1:0                     |  ✅  |
+| Nova-Micro                 | us.amazon.nova-micro-v1:0                    |  ❌  |
+| GPT-OSS-120B               | openai.gpt-oss-120b-1:0                      |  ❌  |
+| GPT-OSS-120B-Thinking      | openai.gpt-oss-120b-1:0                      |  ❌  |
+| GPT-OSS-20B                | openai.gpt-oss-20b-1:0                       |  ❌  |
+| GPT-OSS-20B-Thinking       | openai.gpt-oss-20b-1:0                       |  ❌  |
 | Llama-3-3-70b              | us.meta.llama3-3-70b-instruct-v1:0           |  ❌  |
 | Llama-3-2-1b               | us.meta.llama3-2-1b-instruct-v1:0            |  ❌  |
 | Llama-3-2-3b               | us.meta.llama3-2-3b-instruct-v1:0            |  ❌  |
@@ -208,6 +214,7 @@ const openaiChatCompletionsCreateObject = {
 **Model Support:**
 - ✅ **Claude models**: Fully supported (up to 8,191 sequences)
 - ✅ **Nova models**: Fully supported (up to 4 sequences)  
+- ✅ **GPT-OSS models**: Fully supported
 - ✅ **Mistral models**: Fully supported (up to 10 sequences)
 - ❌ **Llama models**: Not supported (AWS Bedrock limitation)
 

package/bedrock-models.js

@@ -6,6 +6,66 @@
 //       https://us-west-2.console.aws.amazon.com/bedrock/home?region=us-west-2#/cross-region-inference
 
 export const bedrock_models = [
+    {
+        // =====================
+        // == Claude 4.1 Opus ==
+        // =====================
+        "modelName":                     "Claude-4-1-Opus",
+        // "modelId":                       "anthropic.claude-opus-4-1-20250805-v1:0",
+        "modelId":                       "us.anthropic.claude-opus-4-1-20250805-v1:0",
+        "vision":                        true,
+        "messages_api":                  true,
+        "system_as_separate_field":      true,
+        "display_role_names":            true,
+        "max_tokens_param_name":         "max_tokens",
+        "max_supported_response_tokens": 131072,
+        "stop_sequences_param_name":     "stop_sequences",
+        "response_chunk_element":        "delta.text",
+        "response_nonchunk_element":     "content[0].text",
+        "thinking_response_chunk_element": "delta.thinking",
+        "thinking_response_nonchunk_element": "content[0].thinking",
+        "special_request_schema": {
+            "anthropic_version": "bedrock-2023-05-31",
+            "anthropic_beta": ["output-128k-2025-02-19"],
+        },
+        "image_support": {
+            "max_image_size": 20971520, // 20MB
+            "supported_formats": ["jpeg", "png", "gif", "webp"],
+            "max_images_per_request": 10
+        }
+    },
+    {
+        // ==============================
+        // == Claude 4.1 Opus Thinking ==
+        // ==============================
+        "modelName":                     "Claude-4-1-Opus-Thinking",
+        // "modelId":                       "anthropic.claude-opus-4-1-20250805-v1:0",
+        "modelId":                       "us.anthropic.claude-opus-4-1-20250805-v1:0",
+        "vision":                        true,
+        "messages_api":                  true,
+        "system_as_separate_field":      true,
+        "display_role_names":            true,
+        "max_tokens_param_name":         "max_tokens",
+        "max_supported_response_tokens": 131072,
+        "stop_sequences_param_name":     "stop_sequences",
+        "response_chunk_element":        "delta.text",
+        "response_nonchunk_element":     "content[0].text",
+        "thinking_response_chunk_element": "delta.thinking",
+        "thinking_response_nonchunk_element": "content[0].thinking",
+        "special_request_schema": {
+            "anthropic_version": "bedrock-2023-05-31",
+            "anthropic_beta": ["output-128k-2025-02-19"],
+            "thinking": {
+                "type": "enabled",
+                "budget_tokens": 16000
+            },
+        },
+        "image_support": {
+            "max_image_size": 20971520, // 20MB
+            "supported_formats": ["jpeg", "png", "gif", "webp"],
+            "max_images_per_request": 10
+        }
+    },
     {
         // ====================
         // == Claude 4 Opus ==
@@ -618,6 +678,84 @@ export const bedrock_models = [
             "inferenceConfig": {}
         }
     },
+    {
+        // ====================
+        // == GPT-OSS-120B ==
+        // ====================
+        "modelName":                     "GPT-OSS-120B",
+        "modelId":                       "openai.gpt-oss-120b-1:0",
+        // "modelId":                       "us.openai.gpt-oss-120b-1:0",
+        "vision":                        false,
+        "messages_api":                  true,
+        "system_as_separate_field":      false,
+        "display_role_names":            true,
+        "max_tokens_param_name":         "max_completion_tokens",
+        "max_supported_response_tokens": 5000,
+        "stop_sequences_param_name":     "stop_sequences",
+        "response_chunk_element":        "choices[0].delta.content",
+        "response_nonchunk_element":     "choices[0].message.content",
+        "streaming_supported":           false,
+        "special_request_schema": {}
+    },
+    {
+        // ===================
+        // == GPT-OSS-20B ==
+        // ===================
+        "modelName":                     "GPT-OSS-20B",
+        "modelId":                       "openai.gpt-oss-20b-1:0",
+        // "modelId":                       "us.openai.gpt-oss-20b-1:0",
+        "vision":                        false,
+        "messages_api":                  true,
+        "system_as_separate_field":      false,
+        "display_role_names":            true,
+        "max_tokens_param_name":         "max_completion_tokens",
+        "max_supported_response_tokens": 5000,
+        "stop_sequences_param_name":     "stop_sequences",
+        "response_chunk_element":        "choices[0].delta.content",
+        "response_nonchunk_element":     "choices[0].message.content",
+        "streaming_supported":           false,
+        "special_request_schema": {}
+    },
+    {
+        // ==============================
+        // == GPT-OSS-120B-Thinking ==
+        // ==============================
+        "modelName":                     "GPT-OSS-120B-Thinking",
+        "modelId":                       "openai.gpt-oss-120b-1:0",
+        // "modelId":                       "us.openai.gpt-oss-120b-1:0",
+        "vision":                        false,
+        "messages_api":                  true,
+        "system_as_separate_field":      false,
+        "display_role_names":            true,
+        "max_tokens_param_name":         "max_completion_tokens",
+        "max_supported_response_tokens": 5000,
+        "stop_sequences_param_name":     "stop_sequences",
+        "response_chunk_element":        "choices[0].delta.content",
+        "response_nonchunk_element":     "choices[0].message.content",
+        "streaming_supported":           false,
+        "preserve_reasoning":            true,
+        "special_request_schema": {}
+    },
+    {
+        // =============================
+        // == GPT-OSS-20B-Thinking ==
+        // =============================
+        "modelName":                     "GPT-OSS-20B-Thinking",
+        "modelId":                       "openai.gpt-oss-20b-1:0",
+        // "modelId":                       "us.openai.gpt-oss-20b-1:0",
+        "vision":                        false,
+        "messages_api":                  true,
+        "system_as_separate_field":      false,
+        "display_role_names":            true,
+        "max_tokens_param_name":         "max_completion_tokens",
+        "max_supported_response_tokens": 5000,
+        "stop_sequences_param_name":     "stop_sequences",
+        "response_chunk_element":        "choices[0].delta.content",
+        "response_nonchunk_element":     "choices[0].message.content",
+        "streaming_supported":           false,
+        "preserve_reasoning":            true,
+        "special_request_schema": {}
+    },
     {
         // ================
         // == Mistral-7b ==

package/bedrock-wrapper.js

@@ -62,6 +62,25 @@ async function processImage(imageInput) {
     return processedImage.toString('base64');
 }
 
+function processReasoningTags(text, awsModel) {
+    if (!text) return text;
+    
+    // Check if this is a GPT-OSS model (has reasoning tags)
+    const hasReasoningTags = text.includes('<reasoning>') && text.includes('</reasoning>');
+    
+    if (!hasReasoningTags) {
+        return text;
+    }
+    
+    // If model should preserve reasoning, return as-is
+    if (awsModel.preserve_reasoning) {
+        return text;
+    }
+    
+    // Strip reasoning tags for non-thinking GPT-OSS models
+    return text.replace(/<reasoning>[\s\S]*?<\/reasoning>/g, '').trim();
+}
+
 export async function* bedrockWrapper(awsCreds, openaiChatCompletionsCreateObject, { logging = false } = {} ) {
     const { region, accessKeyId, secretAccessKey } = awsCreds;
     let { messages, model, max_tokens, stream, temperature, top_p, include_thinking_data, stop, stop_sequences } = openaiChatCompletionsCreateObject;
@@ -341,7 +360,11 @@ export async function* bedrockWrapper(awsCreds, openaiChatCompletionsCreateObjec
         console.log("\nFinal request:", JSON.stringify(request, null, 2));
     }
 
-    if (stream) {
+    // Check if model supports streaming, override stream parameter if not
+    const modelSupportsStreaming = awsModel.streaming_supported !== false;
+    const shouldStream = stream && modelSupportsStreaming;
+
+    if (shouldStream) {
         const responseStream = await client.send(
             new InvokeModelWithResponseStreamCommand({
                 contentType: "application/json",
@@ -361,6 +384,8 @@ export async function* bedrockWrapper(awsCreds, openaiChatCompletionsCreateObjec
                     is_thinking = false;
                     result = `</think>\n\n${result}`;
                 }
+                // Process reasoning tags for GPT-OSS models
+                result = processReasoningTags(result, awsModel);
                 yield result;
             } else {
                 if (include_thinking_data && awsModel.thinking_response_chunk_element) {
@@ -417,6 +442,9 @@ export async function* bedrockWrapper(awsCreds, openaiChatCompletionsCreateObjec
             text_result = "";
         }
 
+        // Process reasoning tags for GPT-OSS models
+        text_result = processReasoningTags(text_result, awsModel);
+
         let result = thinking_result ? `<think>${thinking_result}</think>\n\n${text_result}` : text_result;
         
         // Ensure final result is a string, in case thinking_result was also empty

package/logs/7aa436f5-0b5d-44bd-8860-e1a898f87df2/notification.json

@@ -0,0 +1,65 @@
+[
+  {
+    "session_id": "7aa436f5-0b5d-44bd-8860-e1a898f87df2",
+    "transcript_path": "C:\\Users\\Justin.Parker\\.claude\\projects\\C--git-bedrock-wrapper\\7aa436f5-0b5d-44bd-8860-e1a898f87df2.jsonl",
+    "cwd": "C:\\git\\bedrock-wrapper",
+    "hook_event_name": "Notification",
+    "message": "Claude needs your permission to use Fetch"
+  },
+  {
+    "session_id": "7aa436f5-0b5d-44bd-8860-e1a898f87df2",
+    "transcript_path": "C:\\Users\\Justin.Parker\\.claude\\projects\\C--git-bedrock-wrapper\\7aa436f5-0b5d-44bd-8860-e1a898f87df2.jsonl",
+    "cwd": "C:\\git\\bedrock-wrapper",
+    "hook_event_name": "Notification",
+    "message": "Claude needs your permission to use Fetch"
+  },
+  {
+    "session_id": "7aa436f5-0b5d-44bd-8860-e1a898f87df2",
+    "transcript_path": "C:\\Users\\Justin.Parker\\.claude\\projects\\C--git-bedrock-wrapper\\7aa436f5-0b5d-44bd-8860-e1a898f87df2.jsonl",
+    "cwd": "C:\\git\\bedrock-wrapper",
+    "hook_event_name": "Notification",
+    "message": "Claude needs your permission to use "
+  },
+  {
+    "session_id": "7aa436f5-0b5d-44bd-8860-e1a898f87df2",
+    "transcript_path": "C:\\Users\\Justin.Parker\\.claude\\projects\\C--git-bedrock-wrapper\\7aa436f5-0b5d-44bd-8860-e1a898f87df2.jsonl",
+    "cwd": "C:\\git\\bedrock-wrapper",
+    "hook_event_name": "Notification",
+    "message": "Claude is waiting for your input"
+  },
+  {
+    "session_id": "7aa436f5-0b5d-44bd-8860-e1a898f87df2",
+    "transcript_path": "C:\\Users\\Justin.Parker\\.claude\\projects\\C--git-bedrock-wrapper\\7aa436f5-0b5d-44bd-8860-e1a898f87df2.jsonl",
+    "cwd": "C:\\git\\bedrock-wrapper",
+    "hook_event_name": "Notification",
+    "message": "Claude is waiting for your input"
+  },
+  {
+    "session_id": "7aa436f5-0b5d-44bd-8860-e1a898f87df2",
+    "transcript_path": "C:\\Users\\Justin.Parker\\.claude\\projects\\C--git-bedrock-wrapper\\7aa436f5-0b5d-44bd-8860-e1a898f87df2.jsonl",
+    "cwd": "C:\\git\\bedrock-wrapper",
+    "hook_event_name": "Notification",
+    "message": "Claude is waiting for your input"
+  },
+  {
+    "session_id": "7aa436f5-0b5d-44bd-8860-e1a898f87df2",
+    "transcript_path": "C:\\Users\\Justin.Parker\\.claude\\projects\\C--git-bedrock-wrapper\\7aa436f5-0b5d-44bd-8860-e1a898f87df2.jsonl",
+    "cwd": "C:\\git\\bedrock-wrapper",
+    "hook_event_name": "Notification",
+    "message": "Claude needs your permission to use "
+  },
+  {
+    "session_id": "7aa436f5-0b5d-44bd-8860-e1a898f87df2",
+    "transcript_path": "C:\\Users\\Justin.Parker\\.claude\\projects\\C--git-bedrock-wrapper\\7aa436f5-0b5d-44bd-8860-e1a898f87df2.jsonl",
+    "cwd": "C:\\git\\bedrock-wrapper",
+    "hook_event_name": "Notification",
+    "message": "Claude is waiting for your input"
+  },
+  {
+    "session_id": "7aa436f5-0b5d-44bd-8860-e1a898f87df2",
+    "transcript_path": "C:\\Users\\Justin.Parker\\.claude\\projects\\C--git-bedrock-wrapper\\7aa436f5-0b5d-44bd-8860-e1a898f87df2.jsonl",
+    "cwd": "C:\\git\\bedrock-wrapper",
+    "hook_event_name": "Notification",
+    "message": "Claude is waiting for your input"
+  }
+]