@langchain/aws does not properly parse gpt-oss content blocks

[jmroon]

Checked other resources

• This is a bug, not a usage question. For questions, please use the LangChain Forum (https://forum.langchain.com/).
• I added a very descriptive title to this issue.
• I searched the LangChain.js documentation with the integrated search.
• I used the GitHub search to find a similar question and didn't find it.
• I am sure that this is a bug in LangChain.js rather than my code.
• The bug is not resolved by updating to the latest stable version of LangChain (or the specific integration package).

Example Code

import { ChatBedrockConverse } from "@langchain/aws";

const bedrock = new ChatBedrockConverse({
  model: "openai.gpt-oss-120b-1:0",
  region: "us-east-1",
  performanceConfig: {
    latency: 'optimized',
  },
  credentials: {
    accessKeyId: ACCESS_KEY_ID,
    secretAccessKey: SECRET_ACCESS_KEY,
  },
});

const aiMsg = await bedrock.invoke([
  [ "system", "You are a helpful assistant."],
  ["human", "How are you?"],
])
console.log(JSON.stringify(aiMsg.contentBlocks, null, 2));

Error Message and Stack Trace (if applicable)

No response

Description

ReasoningContentBlock is not being correctly inferred from AWS Bedrock gpt-oss model responses.

Actual response:

[
  {
    "type": "non_standard",
    "value": {
      "type": "reasoning_content",
      "reasoningText": {
        "text": "The user asks \"How are you?\" It's a casual question. I respond politely."
      }
    }
  },
  {
    "type": "text",
    "text": "I'm doing great, thank you! How can I assist you today?"
  }
]

Expected response:

[
  {
    "type": "reasoning",
     "reasoning": "The user asks \"How are you?\" It's a casual question. I respond politely."
  },
  {
    "type": "text",
    "text": "I'm doing great, thank you! How can I assist you today?"
  }
]

System Info

langchain@1.0.2
mac
Node v23.11.1
pnpm 10.19.0