actions/ai-inference
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

update dist

Browse Source
This commit is contained in:
Paulo Santos
2026-02-15 00:26:15 +00:00
committed by GitHub
parent 27965bc3a4
commit e608d2ba8a
4 changed files with 33 additions and 35 deletions
Download Patch File Download Diff File Expand all files Collapse all files

48
README.md
View File

@@ -140,12 +140,12 @@ modelParameters:
temperature: 0.7
```
| Key | Type | Description |
| --------------------- | ------ | -------------------------------------------------------------- |
| `maxCompletionTokens` | number | The maximum number of tokens to generate |
| `maxTokens` | number | The maximum number of tokens to generate (deprecated) |
| `temperature` | number | The sampling temperature to use (0-1) |
| `topP` | number | The nucleus sampling parameter to use (0-1) |
| Key | Type | Description |
| --------------------- | ------ | ----------------------------------------------------- |
| `maxCompletionTokens` | number | The maximum number of tokens to generate |
| `maxTokens` | number | The maximum number of tokens to generate (deprecated) |
| `temperature` | number | The sampling temperature to use (0-1) |
| `topP` | number | The nucleus sampling parameter to use (0-1) |
> ![Note]
> Parameters set in `modelParameters` take precedence over the corresponding action inputs.
@@ -303,24 +303,24 @@ perform actions like searching issues and PRs.
Various inputs are defined in [`action.yml`](action.yml) to let you configure
the action:
| Name | Description | Default |
| -------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------ |
| `token` | Token to use for inference. Typically the GITHUB_TOKEN secret | `github.token` |
| `prompt` | The prompt to send to the model | N/A |
| `prompt-file` | Path to a file containing the prompt (supports .txt and .prompt.yml formats). If both `prompt` and `prompt-file` are provided, `prompt-file` takes precedence | `""` |
| `input` | Template variables in YAML format for .prompt.yml files (e.g., `var1: value1` on separate lines) | `""` |
| `file_input` | Template variables in YAML where values are file paths. The file contents are read and used for templating | `""` |
| `system-prompt` | The system prompt to send to the model | `"You are a helpful assistant"` |
| `system-prompt-file` | Path to a file containing the system prompt. If both `system-prompt` and `system-prompt-file` are provided, `system-prompt-file` takes precedence | `""` |
| `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 maximum number of tokens to generate (deprecated, use `max-completion-tokens` instead) | 200 |
| `max-completion-tokens` | The maximum number of tokens to generate | `""` |
| `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. | `""` |
| Name | Description | Default |
| ----------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------ |
| `token` | Token to use for inference. Typically the GITHUB_TOKEN secret | `github.token` |
| `prompt` | The prompt to send to the model | N/A |
| `prompt-file` | Path to a file containing the prompt (supports .txt and .prompt.yml formats). If both `prompt` and `prompt-file` are provided, `prompt-file` takes precedence | `""` |
| `input` | Template variables in YAML format for .prompt.yml files (e.g., `var1: value1` on separate lines) | `""` |
| `file_input` | Template variables in YAML where values are file paths. The file contents are read and used for templating | `""` |
| `system-prompt` | The system prompt to send to the model | `"You are a helpful assistant"` |
| `system-prompt-file` | Path to a file containing the system prompt. If both `system-prompt` and `system-prompt-file` are provided, `system-prompt-file` takes precedence | `""` |
| `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 maximum number of tokens to generate (deprecated, use `max-completion-tokens` instead) | 200 |
| `max-completion-tokens` | The maximum number of tokens to generate | `""` |
| `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. | `""` |
## Outputs

3
dist/index.js generated vendored
View File

@@ -58300,7 +58300,6 @@ OpenAI.Responses = Responses;
OpenAI.Evals = Evals;
OpenAI.Containers = Containers;
// Note: solution around models using different underlying max tokens properties
/**
* Build according to what input was passed, default to max_tokens.
* Only one of max_tokens or max_completion_tokens will be set.
@@ -58366,7 +58365,7 @@ async function mcpInference(request, githubMcpClient) {
model: request.modelName,
temperature: request.temperature,
top_p: request.topP,
...buildMaxTokensParam(request),
...buildMaxTokensParam(request), // Note: solution around models using different underlying max tokens properties
};
// Add response format if specified (only on final iteration to avoid conflicts with tool calls)
if (finalMessage && request.responseFormat) {

2
dist/index.js.map generated vendored
View File

File diff suppressed because one or more lines are too long

15
src/inference.ts
View File

@@ -1,6 +1,6 @@
import * as core from '@actions/core'
import OpenAI from 'openai'
import { GitHubMCPClient, executeToolCalls, ToolCall } from './mcp.js'
import {GitHubMCPClient, executeToolCalls, ToolCall} from './mcp.js'
interface ChatMessage {
role: 'system' | 'user' | 'assistant' | 'tool'
@@ -10,7 +10,7 @@ interface ChatMessage {
}
export interface InferenceRequest {
messages: Array<{ role: 'system' | 'user' | 'assistant' | 'tool'; content: string }>
messages: Array<{role: 'system' | 'user' | 'assistant' | 'tool'; content: string}>
modelName: string
maxTokens?: number // Deprecated
maxCompletionTokens?: number
@@ -18,7 +18,7 @@ export interface InferenceRequest {
token: string
temperature?: number
topP?: number
responseFormat?: { type: 'json_schema'; json_schema: unknown } // Processed response format for the API
responseFormat?: {type: 'json_schema'; json_schema: unknown} // Processed response format for the API
customHeaders?: Record<string, string> // Custom HTTP headers to include in API requests
}
@@ -34,17 +34,16 @@ export interface InferenceResponse {
}>
}
/**
* Build according to what input was passed, default to max_tokens.
* Only one of max_tokens or max_completion_tokens will be set.
*/
function buildMaxTokensParam(request: InferenceRequest): { max_tokens?: number; max_completion_tokens?: number } {
function buildMaxTokensParam(request: InferenceRequest): {max_tokens?: number; max_completion_tokens?: number} {
if (request.maxCompletionTokens != null) {
return { max_completion_tokens: request.maxCompletionTokens }
return {max_completion_tokens: request.maxCompletionTokens}
}
if (request.maxTokens != null) {
return { max_tokens: request.maxTokens }
return {max_tokens: request.maxTokens}
}
return {}
}
@@ -137,7 +136,7 @@ export async function mcpInference(
messages.push({
role: 'assistant',
content: modelResponse || '',
...(toolCalls && { tool_calls: toolCalls as ToolCall[] }),
...(toolCalls && {tool_calls: toolCalls as ToolCall[]}),
})
if (!toolCalls || toolCalls.length === 0) {