bedrock-wrapper 2.6.2 → 2.7.0

package/.example.env

@@ -1,13 +1,12 @@
-# ========================
-# == AWS AUTH VARIABLES ==
-# ========================
-AWS_REGION = "us-west-2"
-AWS_ACCESS_KEY_ID = "AKxxxxxxxxxxxxxxxxxx"
-AWS_SECRET_ACCESS_KEY = "xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"
-
-# ================
-# == LLM PARAMS ==
-# ================
-LLM_MAX_GEN_TOKENS = 800
-LLM_TEMPERATURE = 0.1
-LLM_TOP_P = 0.9
+# ========================
+# == AWS AUTH VARIABLES ==
+# ========================
+AWS_REGION = "us-west-2"
+AWS_ACCESS_KEY_ID = "AKxxxxxxxxxxxxxxxxxx"
+AWS_SECRET_ACCESS_KEY = "xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"
+
+# ================
+# == LLM PARAMS ==
+# ================
+LLM_MAX_GEN_TOKENS = 800
+LLM_TEMPERATURE = 0.2

package/CHANGELOG.md

@@ -1,8 +1,38 @@
 # Changelog
 All notable changes to this project will be documented in this file.
 
+## [2.7.0] - 2025-11-18 (DeepSeek & Qwen 3)
+### ✨ Added
+- Support for DeepSeek foundation models
+  - DeepSeek-R1 (reasoning model with chain-of-thought capabilities, 8K max output tokens)
+  - DeepSeek-V3.1 (hybrid thinking mode for complex reasoning, 8K max output tokens, **Converse API only**)
+- Support for Qwen 3 foundation models
+  - Qwen3-32B (dense architecture, 32K max output tokens)
+  - Qwen3-Coder-30B-A3B (MoE architecture for code generation, 32K max output tokens)
+  - Qwen3-235B-A22B-2507 (MoE architecture for general reasoning, 32K max output tokens)
+  - Qwen3-Coder-480B-A35B (MoE architecture for advanced software engineering, 32K max output tokens)
+- Reasoning content extraction for DeepSeek-R1 via `reasoningContent.reasoningText`
+- Stop sequences support (max 10 items) for DeepSeek and Qwen models
+- Text-to-text completion with streaming support
+- MIT-licensed open weight models for commercial use (DeepSeek)
+- `converse_api_only` flag for models that only support Converse API (automatically forces `useConverseAPI = true`)
+- Long-context handling support for Qwen 3 (up to 256K tokens natively, 1M with extrapolation)
+- Hybrid thinking modes for complex problem-solving vs. fast responses
+- Repository-scale code analysis capabilities for Qwen Coder models
+
+### 🤬 Breaking Changes
+- Removed `top_p` parameter from all models as it is not fully supported by AWS Bedrock
+  - `temperature` should always be used instead
+
+### ⚙️ Technical Details
+- **Model Configuration**: All new models use messages API format (OpenAI-compatible)
+- **API Compatibility**:
+  - Qwen 3 models: Support both Invoke API and Converse API
+  - DeepSeek-R1: Supports both Invoke API and Converse API
+  - DeepSeek-V3.1: Converse API only (automatically enforced)
+
 ## [2.6.2] - 2025-10-16 (Claude Haiku 4.5)
-### Added
+### ✨ Added
 - Support for Claude Haiku 4.5 models
   - Claude-4-5-Haiku
   - Claude-4-5-Haiku-Thinking
@@ -12,16 +42,16 @@ All notable changes to this project will be documented in this file.
 - Temperature/Top-P mutual exclusion parameter handling for Haiku 4.5 models
 
 ## [2.6.1] - 2025-09-30 (Claude Sonnet 4.5)
-### Added
+### ✨ Added
 - Support for Claude Sonnet 4.5 models
   - Claude-4-5-Sonnet
   - Claude-4-5-Sonnet-Thinking
 
 ## [2.5.0] - 2025-08-12 (Converse API)
-### Added
+### ✨ Added
 - Support for Converse API (streaming and non-streaming)
 
-### Technical Details
+### ⚙️ Technical Details
 - **Model Configuration**: All models use standard messages API format
 - **API Compatibility**: Supports OpenAI-style requests
 - **Response Processing**: Automatic reasoning tag handling based on model variant
@@ -29,7 +59,7 @@ All notable changes to this project will be documented in this file.
 - **Testing Coverage**: Full integration with existing test suites and interactive example
 
 ## [2.4.5] - 2025-08-06 (GPT-OSS Models)
-### Added
+### ✨ 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)
@@ -41,7 +71,7 @@ All notable changes to this project will be documented in this file.
 - Non-streaming support for GPT-OSS models (streaming not supported by AWS Bedrock)
 - OpenAI-compatible API format with `max_completion_tokens` parameter
 
-### Technical Details
+### ⚙️ 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
@@ -49,13 +79,13 @@ All notable changes to this project will be documented in this file.
 - **Testing Coverage**: Full integration with existing test suites and interactive example
 
 ## [2.4.4] - 2025-08-05 (Claude 4.1 Opus)
-### Added
+### ✨ 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
+### 🛠️ Fixed
 - **Critical Discovery**: Removed stop sequences support from Llama models
   - AWS Bedrock does not support stop sequences for Llama models (confirmed via official AWS documentation)
   - Llama models only support: `prompt`, `temperature`, `top_p`, `max_gen_len`, `images`
@@ -64,7 +94,7 @@ All notable changes to this project will be documented in this file.
   - Removed conflicting empty `inferenceConfig: {}` from Nova model configurations
 - Improved error handling for empty responses when stop sequences trigger early
 
-### Updated
+### 📝 Updated
 - **Documentation corrections**
   - Corrected stop sequences support claims (removed "all models support" language)
   - Added accurate model-specific support matrix with sequence limits
@@ -75,14 +105,14 @@ All notable changes to this project will be documented in this file.
   - ✅ Mistral models: Full support (up to 10 sequences)
   - ❌ Llama models: Not supported (AWS Bedrock limitation)
 
-### Technical Details
+### ⚙️ Technical Details
 - Based on comprehensive research of official AWS Bedrock documentation
 - All changes maintain full backward compatibility
 - Test results show significant improvements in stop sequences reliability for supported models
 - Added detailed explanations to help users understand AWS Bedrock's actual capabilities
 
 ## [2.4.2] - 2025-07-31 (Stop Sequences Support)
-### Added
+### ✨ Added
 - Stop sequences support for compatible models
   - OpenAI-compatible `stop` and `stop_sequences` parameters
   - Automatic string-to-array conversion for compatibility
@@ -90,7 +120,7 @@ All notable changes to this project will be documented in this file.
 - Enhanced request building logic to include stop sequences in appropriate API formats
 - Comprehensive stop sequences testing and validation with `npm run test-stop`
 
-### Fixed
+### 🛠️ Fixed
 - **Critical Discovery**: Removed stop sequences support from Llama models
   - AWS Bedrock does not support stop sequences for Llama models (confirmed via official documentation)
   - Llama models only support: `prompt`, `temperature`, `top_p`, `max_gen_len`, `images`
@@ -98,7 +128,7 @@ All notable changes to this project will be documented in this file.
 - Fixed Nova model configuration conflicts that were causing stop sequence inconsistencies
 - Improved error handling for empty responses when stop sequences trigger early
 
-### Technical Details
+### ⚙️ Technical Details
 - **Model Support Matrix**:
   - ✅ Claude models: Full support (up to 8,191 sequences)
   - ✅ Nova models: Full support (up to 4 sequences)
@@ -110,7 +140,7 @@ All notable changes to this project will be documented in this file.
 - Added comprehensive documentation in README.md and CLAUDE.md explaining support limitations
 
 ## [2.4.0] - 2025-07-24 (AWS Nova Models)
-### Added
+### ✨ Added
 - Support for AWS Nova models
   - Nova-Pro (300K context, multimodal, 5K output tokens)
   - Nova-Lite (300K context, multimodal, optimized for speed)
@@ -120,7 +150,7 @@ All notable changes to this project will be documented in this file.
 - Automatic content array formatting for Nova message compatibility
 
 ## [2.3.1] - 2025-05-22 (Claude 4 Opus / Sonnet)
-### Added
+### ✨ Added
 - Support for Claude 4 Opus & Claude 4 Sonnet models
   - Claude-4-Opus
   - Claude-4-Opus-Thinking
@@ -128,7 +158,7 @@ All notable changes to this project will be documented in this file.
   - Claude-4-Sonnet-Thinking
 
 ## [2.3.0] - 2025-02-15 (Claude 3.7 & Image Support)
-### Added
+### ✨ Added
 - Support for Claude 3.7 models
   - Claude-3-7-Sonnet
   - Claude-3-7-Sonnet-Thinking
@@ -140,20 +170,20 @@ All notable changes to this project will be documented in this file.
 - Enhanced message handling for multimodal content
 - Documentation for image support usage
 
-### Changed
+### 🔄 Changed
 - Updated model configuration for image-capable models
 - Improved response handling for multimodal inputs
 
 ## [2.2.0] - 2025-01-01 (Llama 3.3 70b)
-### Added
+### ✨ Added
 - Support for Llama 3.3 70b
 
 ## [2.1.0] - 2024-11-21 (Claude 3.5 Haiku)
-### Added
+### ✨ Added
 - Support for Claude 3.5 Haiku
 
 ## [2.0.0] - 2024-10-31 (Claude Sonnet & Haiku)
-### Added
+### ✨ Added
 - Support for Anthropic Sonnet & Haiku models
   - Claude-3-5-Sonnet-v2
   - Claude-3-5-Sonnet
@@ -163,14 +193,14 @@ All notable changes to this project will be documented in this file.
 - Stardardize output to be a string via Streamed and non-Streamed responses  
   > **NOTE:** This is a breaking change for previous non-streaming responses. Existing streaming responses will remain unchanged.
 
-### Changed
+### 🔄 Changed
 - Complete architecture overhaul for better model support
 - Improved message handling with role-based formatting
 - Enhanced error handling and response processing
 - Standardized model configuration format
 - Updated AWS SDK integration
 
-### Technical Details
+### ⚙️ Technical Details
 - Implemented messages API support for compatible models
 - Added system message handling as separate field where supported
 - Configurable token limits per model
@@ -178,7 +208,7 @@ All notable changes to this project will be documented in this file.
 - Cross-region profile support for certain models
 
 ## [1.3.0] - 2024-07-24 (Llama3.2)
-### Added
+### ✨ Added
 - Support for Llama 3.2 series models
   - Llama-3-2-1b
   - Llama-3-2-3b
@@ -186,14 +216,14 @@ All notable changes to this project will be documented in this file.
   - Llama-3-2-90b
 
 ## [1.1.0] - 2024-07-24 (Llama3.1)
-### Added
+### ✨ Added
 - Support for Llama 3.1 series models
   - Llama-3-1-8b
   - Llama-3-1-70b
 
 
 ## [1.0.14] - 2024-05-06 (Initial Stable Release)
-### Added
+### ✨ Added
 - Initial stablerelease of Bedrock Wrapper
 - Basic AWS Bedrock integration
 - OpenAI-compatible API object support

package/LICENSE

@@ -1,21 +1,21 @@
-MIT License
-
-Copyright (c) 2024 Justin Parker
-
-Permission is hereby granted, free of charge, to any person obtaining a copy
-of this software and associated documentation files (the "Software"), to deal
-in the Software without restriction, including without limitation the rights
-to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
-copies of the Software, and to permit persons to whom the Software is
-furnished to do so, subject to the following conditions:
-
-The above copyright notice and this permission notice shall be included in all
-copies or substantial portions of the Software.
-
-THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
-IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
-FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
-AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
-LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
-OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
-SOFTWARE.
+MIT License
+
+Copyright (c) 2024 Justin Parker
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

package/README.md

@@ -43,7 +43,6 @@ Bedrock Wrapper is an npm package that simplifies the integration of existing Op
         "max_tokens": LLM_MAX_GEN_TOKENS,
         "stream": true,
         "temperature": LLM_TEMPERATURE,
-        "top_p": LLM_TOP_P,
         "stop_sequences": ["STOP", "END"], // Optional: sequences that will stop generation
     };
     ```
@@ -158,7 +157,11 @@ Bedrock Wrapper is an npm package that simplifies the integration of existing Op
 | Mistral-7b                 | mistral.mistral-7b-instruct-v0:2             |  ❌  |
 | Mixtral-8x7b               | mistral.mixtral-8x7b-instruct-v0:1           |  ❌  |
 | Mistral-Large              | mistral.mistral-large-2402-v1:0              |  ❌  |
-   
+| Qwen3-32B                  | alibaba.qwen3-32b-instruct-v1:0              |  ❌  |
+| Qwen3-Coder-30B-A3B        | alibaba.qwen3-coder-30b-a3b-instruct-v1:0    |  ❌  |
+| Qwen3-235B-A22B-2507       | alibaba.qwen3-235b-a22b-instruct-2507-v1:0   |  ❌  |
+| Qwen3-Coder-480B-A35B      | alibaba.qwen3-coder-480b-a35b-instruct-v1:0  |  ❌  |
+
 To return the list progrmatically you can import and call `listBedrockWrapperSupportedModels`:  
 ```javascript
 import { listBedrockWrapperSupportedModels } from 'bedrock-wrapper';
@@ -235,9 +238,10 @@ const openaiChatCompletionsCreateObject = {
 
 **Model Support:**
 - ✅ **Claude models**: Fully supported (up to 8,191 sequences)
-- ✅ **Nova models**: Fully supported (up to 4 sequences)  
+- ✅ **Nova models**: Fully supported (up to 4 sequences)
 - ✅ **GPT-OSS models**: Fully supported
 - ✅ **Mistral models**: Fully supported (up to 10 sequences)
+- ✅ **Qwen models**: Fully supported
 - ❌ **Llama models**: Not supported (AWS Bedrock limitation)
 
 **Features:**
@@ -251,7 +255,7 @@ const openaiChatCompletionsCreateObject = {
 // Stop generation when model tries to output "7"
 const result = await bedrockWrapper(awsCreds, {
     messages: [{ role: "user", content: "Count from 1 to 10" }],
-    model: "Claude-3-5-Sonnet",  // Use Claude, Nova, or Mistral models
+    model: "Claude-3-5-Sonnet",  // Use Claude, Nova, Mistral, or Qwen models
     stop_sequences: ["7"]
 });
 // Response: "1, 2, 3, 4, 5, 6," (stops before "7")
@@ -274,27 +278,6 @@ Some AWS Bedrock models have specific parameter restrictions that are automatica
 - Claude-4-Opus & Claude-4-Opus-Thinking
 - Claude-4-1-Opus & Claude-4-1-Opus-Thinking
 
-**Restriction:** These models cannot accept both `temperature` and `top_p` parameters simultaneously.
-
-**Automatic Handling:** When both parameters are provided, the wrapper automatically:
-1. **Keeps `temperature`** (prioritized as more commonly used)
-2. **Removes `top_p`** to prevent validation errors
-3. **Works with both APIs** (Invoke API and Converse API)
-
-```javascript
-const request = {
-    messages: [{ role: "user", content: "Hello" }],
-    model: "Claude-4-5-Sonnet",
-    temperature: 0.7,  // ✅ Kept
-    top_p: 0.9         // ❌ Automatically removed
-};
-
-// No error thrown - wrapper handles the restriction automatically
-const response = await bedrockWrapper(awsCreds, request);
-```
-
-**Why This Happens:** AWS Bedrock enforces this restriction on newer Claude models to ensure optimal performance and prevent conflicting sampling parameters.
-
 ---
 
 ### 🧪 Testing

package/bedrock-models.js

@@ -144,9 +144,6 @@ export const bedrock_models = [
         "response_nonchunk_element":     "content[0].text",
         "thinking_response_chunk_element": "delta.thinking",
         "thinking_response_nonchunk_element": "content[0].thinking",
-        "parameter_restrictions": {
-            "mutually_exclusive": [["temperature", "top_p"]]
-        },
         "special_request_schema": {
             "anthropic_version": "bedrock-2023-05-31",
             "anthropic_beta": ["output-128k-2025-02-19"],
@@ -175,9 +172,6 @@ export const bedrock_models = [
         "response_nonchunk_element":     "content[0].text",
         "thinking_response_chunk_element": "delta.thinking",
         "thinking_response_nonchunk_element": "content[0].thinking",
-        "parameter_restrictions": {
-            "mutually_exclusive": [["temperature", "top_p"]]
-        },
         "special_request_schema": {
             "anthropic_version": "bedrock-2023-05-31",
             "anthropic_beta": ["output-128k-2025-02-19"],
@@ -210,9 +204,6 @@ export const bedrock_models = [
         "response_nonchunk_element":     "content[0].text",
         "thinking_response_chunk_element": "delta.thinking",
         "thinking_response_nonchunk_element": "content[0].thinking",
-        "parameter_restrictions": {
-            "mutually_exclusive": [["temperature", "top_p"]]
-        },
         "special_request_schema": {
             "anthropic_version": "bedrock-2023-05-31",
             "anthropic_beta": ["output-128k-2025-02-19"],
@@ -241,9 +232,6 @@ export const bedrock_models = [
         "response_nonchunk_element":     "content[0].text",
         "thinking_response_chunk_element": "delta.thinking",
         "thinking_response_nonchunk_element": "content[0].thinking",
-        "parameter_restrictions": {
-            "mutually_exclusive": [["temperature", "top_p"]]
-        },
         "special_request_schema": {
             "anthropic_version": "bedrock-2023-05-31",
             "anthropic_beta": ["output-128k-2025-02-19"],
@@ -276,9 +264,6 @@ export const bedrock_models = [
         "response_nonchunk_element":     "content[0].text",
         "thinking_response_chunk_element": "delta.thinking",
         "thinking_response_nonchunk_element": "content[0].thinking",
-        "parameter_restrictions": {
-            "mutually_exclusive": [["temperature", "top_p"]]
-        },
         "special_request_schema": {
             "anthropic_version": "bedrock-2023-05-31",
             "anthropic_beta": ["output-128k-2025-02-19"],
@@ -307,9 +292,6 @@ export const bedrock_models = [
         "response_nonchunk_element":     "content[0].text",
         "thinking_response_chunk_element": "delta.thinking",
         "thinking_response_nonchunk_element": "content[0].thinking",
-        "parameter_restrictions": {
-            "mutually_exclusive": [["temperature", "top_p"]]
-        },
         "special_request_schema": {
             "anthropic_version": "bedrock-2023-05-31",
             "anthropic_beta": ["output-128k-2025-02-19"],
@@ -978,4 +960,120 @@ export const bedrock_models = [
         "stop_sequences_param_name":     "stop",
         "response_chunk_element":        "outputs[0].text"
     },
+    {
+        // ================
+        // == Qwen3-32B ==
+        // ================
+        "modelName":                     "Qwen3-32B",
+        "modelId":                       "qwen.qwen3-32b-v1:0",
+        "vision":                        false,
+        "messages_api":                  true,
+        "system_as_separate_field":      false,
+        "display_role_names":            true,
+        "max_tokens_param_name":         "max_tokens",
+        "max_supported_response_tokens": 32768,
+        "stop_sequences_param_name":     "stop",
+        "response_chunk_element":        "choices[0].delta.content",
+        "response_nonchunk_element":     "choices[0].message.content",
+        "special_request_schema": {}
+    },
+    {
+        // =========================
+        // == Qwen3-Coder-30B-A3B ==
+        // =========================
+        "modelName":                     "Qwen3-Coder-30B-A3B",
+        "modelId":                       "qwen.qwen3-coder-30b-a3b-v1:0",
+        "vision":                        false,
+        "messages_api":                  true,
+        "system_as_separate_field":      false,
+        "display_role_names":            true,
+        "max_tokens_param_name":         "max_tokens",
+        "max_supported_response_tokens": 32768,
+        "stop_sequences_param_name":     "stop",
+        "response_chunk_element":        "choices[0].delta.content",
+        "response_nonchunk_element":     "choices[0].message.content",
+        "special_request_schema": {}
+    },
+    {
+        // ==========================
+        // == Qwen3-235B-A22B-2507 ==
+        // ==========================
+        "modelName":                     "Qwen3-235B-A22B-2507",
+        "modelId":                       "qwen.qwen3-235b-a22b-2507-v1:0",
+        "vision":                        false,
+        "messages_api":                  true,
+        "system_as_separate_field":      false,
+        "display_role_names":            true,
+        "max_tokens_param_name":         "max_tokens",
+        "max_supported_response_tokens": 32768,
+        "stop_sequences_param_name":     "stop",
+        "response_chunk_element":        "choices[0].delta.content",
+        "response_nonchunk_element":     "choices[0].message.content",
+        "special_request_schema": {}
+    },
+    {
+        // ===========================
+        // == Qwen3-Coder-480B-A35B ==
+        // ===========================
+        "modelName":                     "Qwen3-Coder-480B-A35B",
+        "modelId":                       "qwen.qwen3-coder-480b-a35b-v1:0",
+        "vision":                        false,
+        "messages_api":                  true,
+        "system_as_separate_field":      false,
+        "display_role_names":            true,
+        "max_tokens_param_name":         "max_tokens",
+        "max_supported_response_tokens": 32768,
+        "stop_sequences_param_name":     "stop",
+        "response_chunk_element":        "choices[0].delta.content",
+        "response_nonchunk_element":     "choices[0].message.content",
+        "special_request_schema": {}
+    },
+    {
+        // =================
+        // == DeepSeek-R1 ==
+        // =================
+        "modelName":                     "DeepSeek-R1",
+        // "modelId":                       "deepseek.r1-v1:0",
+        "modelId":                       "us.deepseek.r1-v1:0",
+        "vision":                        false,
+        "messages_api":                  false,
+        "bos_text":                      "",
+        "role_system_message_prefix":    "",
+        "role_system_message_suffix":    "",
+        "role_system_prefix":            "",
+        "role_system_suffix":            "",
+        "role_user_message_prefix":      "",
+        "role_user_message_suffix":      "",
+        "role_user_prefix":              "",
+        "role_user_suffix":              "",
+        "role_assistant_message_prefix": "",
+        "role_assistant_message_suffix": "",
+        "role_assistant_prefix":         "",
+        "role_assistant_suffix":         "",
+        "eom_text":                      "",
+        "display_role_names":            false,
+        "max_tokens_param_name":         "max_tokens",
+        "max_supported_response_tokens": 8192,
+        "stop_sequences_param_name":     "stop",
+        "response_chunk_element":        "choices[0].text",
+        "special_request_schema": {}
+    },
+    {
+        // ====================
+        // == DeepSeek-V3.1 ==
+        // ====================
+        "modelName":                     "DeepSeek-V3.1",
+        "modelId":                       "deepseek.v3-v1:0",
+        "vision":                        false,
+        "messages_api":                  true,
+        "converse_api_only":             true,
+        "system_as_separate_field":      false,
+        "display_role_names":            true,
+        "max_tokens_param_name":         "max_tokens",
+        "max_supported_response_tokens": 8192,
+        "stop_sequences_param_name":     "stop",
+        "response_chunk_element":        "choices[0].delta.content",
+        "response_nonchunk_element":     "choices[0].message.content",
+        "special_request_schema": {}
+    },
 ];