fix(sdk)!: add _response to response models to finally fix duplicated names

Author: stainless-app[bot]

.stats.yml

@@ -1,4 +1,4 @@
 configured_endpoints: 4
 openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/isaacus%2Fisaacus-43557cfcc912900321433e1b633b39a81a3bfdbcfc86784aff4ff8219f5ebec4.yml
 openapi_spec_hash: e612b47282935484c5de2ebbd49df824
-config_hash: 886b5eef0dbd90b8e6686e987a07b816
+config_hash: efa2ea406c5ecd6883ff8b0fb428e579

README.md

@@ -26,13 +26,13 @@ const client = new Isaacus({
   apiKey: process.env['ISAACUS_API_KEY'], // This is the default and can be omitted
 });
 
-const universalClassification = await client.classifications.universal.create({
+const universalClassificationResponse = await client.classifications.universal.create({
   model: 'kanon-universal-classifier',
   query: 'This is a confidentiality clause.',
   texts: ['I agree not to tell anyone about the document.'],
 });
 
-console.log(universalClassification.classifications);
+console.log(universalClassificationResponse.classifications);
 ```
 
 ### Request & Response types
@@ -52,7 +52,7 @@ const params: Isaacus.Classifications.UniversalCreateParams = {
   query: 'This is a confidentiality clause.',
   texts: ['I agree not to tell anyone about the document.'],
 };
-const universalClassification: Isaacus.Classifications.UniversalClassification =
+const universalClassificationResponse: Isaacus.Classifications.UniversalClassificationResponse =
   await client.classifications.universal.create(params);
 ```
 
@@ -66,7 +66,7 @@ a subclass of `APIError` will be thrown:
 
 <!-- prettier-ignore -->
 ```ts
-const universalClassification = await client.classifications.universal
+const universalClassificationResponse = await client.classifications.universal
   .create({
     model: 'kanon-universal-classifier',
     query: 'This is a confidentiality clause.',
@@ -162,15 +162,15 @@ const response = await client.classifications.universal
 console.log(response.headers.get('X-My-Header'));
 console.log(response.statusText); // access the underlying Response object
 
-const { data: universalClassification, response: raw } = await client.classifications.universal
+const { data: universalClassificationResponse, response: raw } = await client.classifications.universal
   .create({
     model: 'kanon-universal-classifier',
     query: 'This is a confidentiality clause.',
     texts: ['I agree not to tell anyone about the document.'],
   })
   .withResponse();
 console.log(raw.headers.get('X-My-Header'));
-console.log(universalClassification.classifications);
+console.log(universalClassificationResponse.classifications);
 ```
 
 ### Logging

api.md

@@ -2,42 +2,42 @@
 
 Types:
 
-- <code><a href="./src/resources/embeddings.ts">Embedding</a></code>
+- <code><a href="./src/resources/embeddings.ts">EmbeddingResponse</a></code>
 
 Methods:
 
-- <code title="post /embeddings">client.embeddings.<a href="./src/resources/embeddings.ts">create</a>({ ...params }) -> Embedding</code>
+- <code title="post /embeddings">client.embeddings.<a href="./src/resources/embeddings.ts">create</a>({ ...params }) -> EmbeddingResponse</code>
 
 # Classifications
 
 ## Universal
 
 Types:
 
-- <code><a href="./src/resources/classifications/universal.ts">UniversalClassification</a></code>
+- <code><a href="./src/resources/classifications/universal.ts">UniversalClassificationResponse</a></code>
 
 Methods:
 
-- <code title="post /classifications/universal">client.classifications.universal.<a href="./src/resources/classifications/universal.ts">create</a>({ ...params }) -> UniversalClassification</code>
+- <code title="post /classifications/universal">client.classifications.universal.<a href="./src/resources/classifications/universal.ts">create</a>({ ...params }) -> UniversalClassificationResponse</code>
 
 # Rerankings
 
 Types:
 
-- <code><a href="./src/resources/rerankings.ts">Reranking</a></code>
+- <code><a href="./src/resources/rerankings.ts">RerankingResponse</a></code>
 
 Methods:
 
-- <code title="post /rerankings">client.rerankings.<a href="./src/resources/rerankings.ts">create</a>({ ...params }) -> Reranking</code>
+- <code title="post /rerankings">client.rerankings.<a href="./src/resources/rerankings.ts">create</a>({ ...params }) -> RerankingResponse</code>
 
 # Extractions
 
 ## Qa
 
 Types:
 
-- <code><a href="./src/resources/extractions/qa.ts">AnswerExtraction</a></code>
+- <code><a href="./src/resources/extractions/qa.ts">AnswerExtractionResponse</a></code>
 
 Methods:
 
-- <code title="post /extractions/qa">client.extractions.qa.<a href="./src/resources/extractions/qa.ts">create</a>({ ...params }) -> AnswerExtraction</code>
+- <code title="post /extractions/qa">client.extractions.qa.<a href="./src/resources/extractions/qa.ts">create</a>({ ...params }) -> AnswerExtractionResponse</code>

packages/mcp-server/src/tools/classifications/universal/create-classifications-universal.ts

@@ -18,7 +18,7 @@ export const metadata: Metadata = {
 export const tool: Tool = {
   name: 'create_classifications_universal',
   description:
-    "When using this tool, always use the `jq_filter` parameter to reduce the response size and improve performance.\n\nOnly omit if you're sure you don't need the data.\n\nClassify the relevance of legal documents to a query with an Isaacus universal legal AI classifier.\n\n# Response Schema\n```json\n{\n  $ref: '#/$defs/universal_classification',\n  $defs: {\n    universal_classification: {\n      type: 'object',\n      title: 'Universal classification response',\n      description: 'Classifications of the relevance of legal documents to a query produced by an Isaacus universal legal AI classifier.',\n      properties: {\n        classifications: {\n          type: 'array',\n          description: 'The classifications of the texts, by relevance to the query, in order from highest to lowest relevance score.',\n          items: {\n            type: 'object',\n            title: 'Universal classification',\n            properties: {\n              chunks: {\n                type: 'array',\n                description: 'The text as broken into chunks by [semchunk](https://github.com/isaacus-dev/semchunk), each chunk with its own confidence score, ordered from highest to lowest score.\\n\\nIf no chunking occurred, this will be `null`.',\n                items: {\n                  type: 'object',\n                  title: 'Universal classification chunk',\n                  properties: {\n                    end: {\n                      type: 'integer',\n                      description: 'The index of the character immediately after the last character of the chunk in the original text, beginning from `0` (such that, in Python, the chunk is equivalent to `text[start:end]`).'\n                    },\n                    index: {\n                      type: 'integer',\n                      description: 'The original position of the chunk in the outputted list of chunks before sorting, starting from `0` (and, therefore, ending at the number of chunks minus `1`).'\n                    },\n                    score: {\n                      type: 'number',\n                      description: 'The model\\'s score of the likelihood that the query expressed about the chunk is supported by the chunk.\\n\\nA score greater than `0.5` indicates that the chunk supports the query, while a score less than `0.5` indicates that the chunk does not support the query.'\n                    },\n                    start: {\n                      type: 'integer',\n                      description: 'The index of the character in the original text where the chunk starts, beginning from `0`.'\n                    },\n                    text: {\n                      type: 'string',\n                      description: 'The text of the chunk.'\n                    }\n                  },\n                  required: [                    'end',\n                    'index',\n                    'score',\n                    'start',\n                    'text'\n                  ]\n                }\n              },\n              index: {\n                type: 'integer',\n                description: 'The index of the text in the input array of texts, starting from `0` (and, therefore, ending at the number of texts minus `1`).'\n              },\n              score: {\n                type: 'number',\n                description: 'A score of the likelihood that the query expressed about the text is supported by the text.\\n\\nA score greater than `0.5` indicates that the text supports the query, while a score less than `0.5` indicates that the text does not support the query.'\n              }\n            },\n            required: [              'chunks',\n              'index',\n              'score'\n            ]\n          }\n        },\n        usage: {\n          type: 'object',\n          title: 'Universal classification usage',\n          description: 'Statistics about the usage of resources in the process of classifying the text.',\n          properties: {\n            input_tokens: {\n              type: 'integer',\n              description: 'The number of tokens inputted to the model.'\n            }\n          },\n          required: [            'input_tokens'\n          ]\n        }\n      },\n      required: [        'classifications',\n        'usage'\n      ]\n    }\n  }\n}\n```",
+    "When using this tool, always use the `jq_filter` parameter to reduce the response size and improve performance.\n\nOnly omit if you're sure you don't need the data.\n\nClassify the relevance of legal documents to a query with an Isaacus universal legal AI classifier.\n\n# Response Schema\n```json\n{\n  $ref: '#/$defs/universal_classification_response',\n  $defs: {\n    universal_classification_response: {\n      type: 'object',\n      title: 'Universal classification response',\n      description: 'Classifications of the relevance of legal documents to a query produced by an Isaacus universal legal AI classifier.',\n      properties: {\n        classifications: {\n          type: 'array',\n          description: 'The classifications of the texts, by relevance to the query, in order from highest to lowest relevance score.',\n          items: {\n            type: 'object',\n            title: 'Universal classification',\n            properties: {\n              chunks: {\n                type: 'array',\n                description: 'The text as broken into chunks by [semchunk](https://github.com/isaacus-dev/semchunk), each chunk with its own confidence score, ordered from highest to lowest score.\\n\\nIf no chunking occurred, this will be `null`.',\n                items: {\n                  type: 'object',\n                  title: 'Universal classification chunk',\n                  properties: {\n                    end: {\n                      type: 'integer',\n                      description: 'The index of the character immediately after the last character of the chunk in the original text, beginning from `0` (such that, in Python, the chunk is equivalent to `text[start:end]`).'\n                    },\n                    index: {\n                      type: 'integer',\n                      description: 'The original position of the chunk in the outputted list of chunks before sorting, starting from `0` (and, therefore, ending at the number of chunks minus `1`).'\n                    },\n                    score: {\n                      type: 'number',\n                      description: 'The model\\'s score of the likelihood that the query expressed about the chunk is supported by the chunk.\\n\\nA score greater than `0.5` indicates that the chunk supports the query, while a score less than `0.5` indicates that the chunk does not support the query.'\n                    },\n                    start: {\n                      type: 'integer',\n                      description: 'The index of the character in the original text where the chunk starts, beginning from `0`.'\n                    },\n                    text: {\n                      type: 'string',\n                      description: 'The text of the chunk.'\n                    }\n                  },\n                  required: [                    'end',\n                    'index',\n                    'score',\n                    'start',\n                    'text'\n                  ]\n                }\n              },\n              index: {\n                type: 'integer',\n                description: 'The index of the text in the input array of texts, starting from `0` (and, therefore, ending at the number of texts minus `1`).'\n              },\n              score: {\n                type: 'number',\n                description: 'A score of the likelihood that the query expressed about the text is supported by the text.\\n\\nA score greater than `0.5` indicates that the text supports the query, while a score less than `0.5` indicates that the text does not support the query.'\n              }\n            },\n            required: [              'chunks',\n              'index',\n              'score'\n            ]\n          }\n        },\n        usage: {\n          type: 'object',\n          title: 'Universal classification usage',\n          description: 'Statistics about the usage of resources in the process of classifying the text.',\n          properties: {\n            input_tokens: {\n              type: 'integer',\n              description: 'The number of tokens inputted to the model.'\n            }\n          },\n          required: [            'input_tokens'\n          ]\n        }\n      },\n      required: [        'classifications',\n        'usage'\n      ]\n    }\n  }\n}\n```",
   inputSchema: {
     type: 'object',
     properties: {

packages/mcp-server/src/tools/embeddings/create-embeddings.ts

@@ -18,7 +18,7 @@ export const metadata: Metadata = {
 export const tool: Tool = {
   name: 'create_embeddings',
   description:
-    "When using this tool, always use the `jq_filter` parameter to reduce the response size and improve performance.\n\nOnly omit if you're sure you don't need the data.\n\nEmbed legal texts with an Isaacus legal AI embedder.\n\n# Response Schema\n```json\n{\n  $ref: '#/$defs/embedding',\n  $defs: {\n    embedding: {\n      type: 'object',\n      title: 'Embedding response',\n      description: 'Embeddings of legal texts produced by an Isaacus legal AI embedder.',\n      properties: {\n        embeddings: {\n          type: 'array',\n          description: 'The embeddings of the inputs.',\n          items: {\n            type: 'object',\n            title: 'Content embedding',\n            properties: {\n              embedding: {\n                type: 'array',\n                description: 'The embedding of the content represented as an array of floating point numbers.',\n                items: {\n                  type: 'number'\n                }\n              },\n              index: {\n                type: 'integer',\n                description: 'The position of the content in the input array of contents, starting from `0` (and, therefore, ending at the number of contents minus `1`).'\n              }\n            },\n            required: [              'embedding',\n              'index'\n            ]\n          }\n        },\n        usage: {\n          type: 'object',\n          title: 'Embedding usage',\n          description: 'Statistics about the usage of resources in the process of embedding the inputs.',\n          properties: {\n            input_tokens: {\n              type: 'integer',\n              description: 'The number of tokens inputted to the model.'\n            }\n          },\n          required: [            'input_tokens'\n          ]\n        }\n      },\n      required: [        'embeddings',\n        'usage'\n      ]\n    }\n  }\n}\n```",
+    "When using this tool, always use the `jq_filter` parameter to reduce the response size and improve performance.\n\nOnly omit if you're sure you don't need the data.\n\nEmbed legal texts with an Isaacus legal AI embedder.\n\n# Response Schema\n```json\n{\n  $ref: '#/$defs/embedding_response',\n  $defs: {\n    embedding_response: {\n      type: 'object',\n      title: 'Embedding response',\n      description: 'Embeddings of legal texts produced by an Isaacus legal AI embedder.',\n      properties: {\n        embeddings: {\n          type: 'array',\n          description: 'The embeddings of the inputs.',\n          items: {\n            type: 'object',\n            title: 'Content embedding',\n            properties: {\n              embedding: {\n                type: 'array',\n                description: 'The embedding of the content represented as an array of floating point numbers.',\n                items: {\n                  type: 'number'\n                }\n              },\n              index: {\n                type: 'integer',\n                description: 'The position of the content in the input array of contents, starting from `0` (and, therefore, ending at the number of contents minus `1`).'\n              }\n            },\n            required: [              'embedding',\n              'index'\n            ]\n          }\n        },\n        usage: {\n          type: 'object',\n          title: 'Embedding usage',\n          description: 'Statistics about the usage of resources in the process of embedding the inputs.',\n          properties: {\n            input_tokens: {\n              type: 'integer',\n              description: 'The number of tokens inputted to the model.'\n            }\n          },\n          required: [            'input_tokens'\n          ]\n        }\n      },\n      required: [        'embeddings',\n        'usage'\n      ]\n    }\n  }\n}\n```",
   inputSchema: {
     type: 'object',
     properties: {