Merge pull request #170 from GitPaulo/gitpaulo/update-deprecated-max-tokens

Update deprecated max_tokens to max_completion_tokens

README.md

@@ -288,6 +288,8 @@ the action:
 | `model`              | The model to use for inference. Must be available in the [GitHub Models](https://github.com/marketplace?type=models) catalog                                                                                       | `openai/gpt-4o`                      |
 | `endpoint`           | The endpoint to use for inference. If you're running this as part of an org, you should probably use the org-specific Models endpoint                                                                              | `https://models.github.ai/inference` |
 | `max-tokens`         | The max number of tokens to generate                                                                                                                                                                               | 200                                  |
+| `temperature`        | The sampling temperature to use (0-1)                                                                                                                                                                              | `""`                                 |
+| `top-p`              | The nucleus sampling parameter to use (0-1)                                                                                                                                                                        | `""`                                 |
 | `enable-github-mcp`  | Enable Model Context Protocol integration with GitHub tools                                                                                                                                                        | `false`                              |
 | `github-mcp-token`   | Token to use for GitHub MCP server (defaults to the main token if not specified).                                                                                                                                  | `""`                                 |
 | `custom-headers`     | Custom HTTP headers to include in API requests. Supports both YAML format (`header1: value1`) and JSON format (`{"header1": "value1"}`). Useful for API Management platforms, rate limiting, and request tracking. | `""`                                 |

__tests__/inference.test.ts

@@ -72,7 +72,7 @@ describe('inference.ts', () => {
             content: 'Hello, AI!',
           },
         ],
-        max_tokens: 100,
+        max_completion_tokens: 100,
         model: 'gpt-4',
       })
 
@@ -176,7 +176,7 @@ describe('inference.ts', () => {
             content: 'Hello, AI!',
           },
         ],
-        max_tokens: 100,
+        max_completion_tokens: 100,
         model: 'gpt-4',
         response_format: requestWithResponseFormat.responseFormat,
       })
@@ -228,7 +228,7 @@ describe('inference.ts', () => {
       expect(callArgs.tools).toEqual(mockMcpClient.tools)
       expect(callArgs.response_format).toBeUndefined()
       expect(callArgs.model).toBe('gpt-4')
-      expect(callArgs.max_tokens).toBe(100)
+      expect(callArgs.max_completion_tokens).toBe(100)
 
       // Verify OpenAI client was initialized with empty custom headers
       expect(mockOpenAIClient).toHaveBeenCalledWith({

action.yml

@@ -46,6 +46,14 @@ inputs:
     description: The maximum number of tokens to generate
     required: false
     default: '200'
+  temperature:
+    description: The sampling temperature to use (0-1)
+    required: false
+    default: ''
+  top-p:
+    description: The nucleus sampling parameter to use (0-1)
+    required: false
+    default: ''
   token:
     description: The token to use
     required: false

dist/index.js

@@ -58312,7 +58312,7 @@ async function simpleInference(request) {
     });
     const chatCompletionRequest = {
         messages: request.messages,
-        max_tokens: request.maxTokens,
+        max_completion_tokens: request.maxTokens,
         model: request.modelName,
         temperature: request.temperature,
         top_p: request.topP,
@@ -58349,7 +58349,7 @@ async function mcpInference(request, githubMcpClient) {
         coreExports.info(`MCP inference iteration ${iterationCount}`);
         const chatCompletionRequest = {
             messages: messages,
-            max_tokens: request.maxTokens,
+            max_completion_tokens: request.maxTokens,
             model: request.modelName,
             temperature: request.temperature,
             top_p: request.topP,
@@ -61548,11 +61548,16 @@ async function run() {
         const githubMcpToken = coreExports.getInput('github-mcp-token') || token;
         const githubMcpToolsets = coreExports.getInput('github-mcp-toolsets');
         const endpoint = coreExports.getInput('endpoint');
+        // Get temperature and topP (prompt YAML modelParameters takes precedence over action inputs)
+        const temperatureInput = coreExports.getInput('temperature');
+        const topPInput = coreExports.getInput('top-p');
+        const temperature = promptConfig?.modelParameters?.temperature ?? (temperatureInput ? parseFloat(temperatureInput) : undefined);
+        const topP = promptConfig?.modelParameters?.topP ?? (topPInput ? parseFloat(topPInput) : undefined);
         // Parse custom headers
         const customHeadersInput = coreExports.getInput('custom-headers');
         const customHeaders = parseCustomHeaders(customHeadersInput);
         // Build the inference request with pre-processed messages and response format
-        const inferenceRequest = buildInferenceRequest(promptConfig, systemPrompt, prompt, modelName, promptConfig?.modelParameters?.temperature, promptConfig?.modelParameters?.topP, maxTokens, endpoint, token, customHeaders);
+        const inferenceRequest = buildInferenceRequest(promptConfig, systemPrompt, prompt, modelName, temperature, topP, maxTokens, endpoint, token, customHeaders);
         const enableMcp = coreExports.getBooleanInput('enable-github-mcp') || false;
         let modelResponse = null;
         if (enableMcp) {

package-lock.json

@@ -11,6 +11,7 @@
       "dependencies": {
         "@actions/core": "^1.11.1",
         "@modelcontextprotocol/sdk": "^1.25.2",
+        "@rollup/rollup-linux-x64-gnu": "4.57.1",
         "@types/tmp": "^0.2.6",
         "js-yaml": "^4.1.1",
         "openai": "^5.11.0",
@@ -2389,9 +2390,9 @@
       ]
     },
     "node_modules/@rollup/rollup-linux-x64-gnu": {
-      "version": "4.52.5",
-      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-x64-gnu/-/rollup-linux-x64-gnu-4.52.5.tgz",
-      "integrity": "sha512-hXGLYpdhiNElzN770+H2nlx+jRog8TyynpTVzdlc6bndktjKWyZyiCsuDAlpd+j+W+WNqfcyAWz9HxxIGfZm1Q==",
+      "version": "4.57.1",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-x64-gnu/-/rollup-linux-x64-gnu-4.57.1.tgz",
+      "integrity": "sha512-ABca4ceT4N+Tv/GtotnWAeXZUZuM/9AQyCyKYyKnpk4yoA7QIAuBt6Hkgpw8kActYlew2mvckXkvx0FfoInnLg==",
       "cpu": [
         "x64"
       ],
@@ -6653,9 +6654,9 @@
       }
     },
     "node_modules/lodash": {
-      "version": "4.17.21",
-      "resolved": "https://registry.npmjs.org/lodash/-/lodash-4.17.21.tgz",
-      "integrity": "sha512-v2kDEe57lecTulaDIuNTPy3Ry4gLGJ6Z1O3vE1krgXZNrsQ+LFTGHVxVjcXPs17LhbZVGedAJv8XZ1tvj5FvSg==",
+      "version": "4.17.23",
+      "resolved": "https://registry.npmjs.org/lodash/-/lodash-4.17.23.tgz",
+      "integrity": "sha512-LgVTMpQtIopCi79SJeDiP0TfWi5CNEc/L/aRdTh3yIvmZXTnheWpKjSZhnvMl8iXbC1tFg9gdHHDMLoV7CnG+w==",
       "dev": true,
       "license": "MIT"
     },

src/inference.ts

@@ -47,7 +47,7 @@ export async function simpleInference(request: InferenceRequest): Promise<string
 
   const chatCompletionRequest: OpenAI.Chat.Completions.ChatCompletionCreateParams = {
     messages: request.messages as OpenAI.Chat.Completions.ChatCompletionMessageParam[],
-    max_tokens: request.maxTokens,
+    max_completion_tokens: request.maxTokens,
     model: request.modelName,
     temperature: request.temperature,
     top_p: request.topP,
@@ -95,7 +95,7 @@ export async function mcpInference(
 
     const chatCompletionRequest: OpenAI.Chat.Completions.ChatCompletionCreateParams = {
       messages: messages as OpenAI.Chat.Completions.ChatCompletionMessageParam[],
-      max_tokens: request.maxTokens,
+      max_completion_tokens: request.maxTokens,
       model: request.modelName,
       temperature: request.temperature,
       top_p: request.topP,

src/main.ts

@@ -65,6 +65,13 @@ export async function run(): Promise<void> {
 
     const endpoint = core.getInput('endpoint')
 
+    // Get temperature and topP (prompt YAML modelParameters takes precedence over action inputs)
+    const temperatureInput = core.getInput('temperature')
+    const topPInput = core.getInput('top-p')
+    const temperature =
+      promptConfig?.modelParameters?.temperature ?? (temperatureInput ? parseFloat(temperatureInput) : undefined)
+    const topP = promptConfig?.modelParameters?.topP ?? (topPInput ? parseFloat(topPInput) : undefined)
+
     // Parse custom headers
     const customHeadersInput = core.getInput('custom-headers')
     const customHeaders = parseCustomHeaders(customHeadersInput)
@@ -75,8 +82,8 @@ export async function run(): Promise<void> {
       systemPrompt,
       prompt,
       modelName,
-      promptConfig?.modelParameters?.temperature,
-      promptConfig?.modelParameters?.topP,
+      temperature,
+      topP,
       maxTokens,
       endpoint,
       token,