ExtractText extracts just the text parts from a Gemini response.

FilterByVendor returns a new VendorsModels containing only the specified vendor's models. Vendor matching is case-insensitive (e.g., "OpenAI", "openai

FindModelNameCaseInsensitive returns the actual model name from available models, matching case-insensitively. Returns empty string if not found. For

Get Load a context from file

GetAllPRs returns all cached PRs

GetGeminiVoiceNames returns just the voice names in alphabetical order

GetNames finds all patterns in the patterns directory and enters the id, name, and pattern into a slice of Entry structs. it returns these entries or

GetPRWithCommits fetches the full PR and its commits.

GetProviderByName returns the provider configuration for a given name with O(1) lookup

GetShowOrEpisodeId extracts show or episode ID from a Spotify URL.

GetTokenFromEnv returns a GitHub token based on the following precedence order: 1. If tokenValue is non-empty, it is returned. 2. Otherwise, if the GI

GetWithoutVariables returns a pattern with only the {{input}} placeholder processed and skips template variable replacement

GrabTranscriptWithArgs retrieves the transcript for the specified video ID using yt-dlp with custom command-line arguments. The language parameter spe

GrabTranscriptWithTimestamps retrieves the transcript with timestamps for the specified video ID using yt-dlp. The language parameter specifies the pr

GrabTranscriptWithTimestampsWithArgs retrieves the transcript with timestamps for the specified video ID using yt-dlp with custom command-line argumen

GrabVisual retrieves visual data from the video by extracting frames via FFmpeg and OCR parsing them via Tesseract.

HtmlReadability Convert HTML input into a clean, readable view args： html (string): full data of web page return： viewContent (string): html main

IsAvailable checks if notifications are available

ListExtensions handles the listextensions flag action

ListModels returns a list of available models.

NewClient creates a new OpenAI-compatible client for the specified provider

NewClient creates a new Vertex AI client for accessing Claude models via Google Cloud

NewContextsHandler creates a new ContextsHandler

NewPatternsHandler creates a new PatternsHandler

NewSessionsHandler creates a new SessionsHandler

NewStorageHandler creates a new StorageHandler

ParseFileChanges extracts and parses the file change marker section from LLM output

ParseResponse parses Gemini API response (candidates/content/parts)

ParseResponse parses Azure OpenAI API response (OpenAI chat completions format)

PopulateDB downloads patterns from the internet and populates the patterns folder

PrepareRequest converts messages to Gemini API format (contents/parts). System messages are extracted into the top-level "systemInstruction" field per

PrintPattern prints the raw contents of the named pattern to the terminal. It checks the custom patterns directory first, then falls back to the main

PrintWithVendor prints models including their vendor on each line. When shellCompleteList is true, output is suitable for shell completion. Default ve

SavePRBatch saves multiple PRs in a single transaction for better performance

ScanDirectory scans a directory and returns a JSON representation of its structure

SearchShows searches for podcasts/shows matching the query.

Send sends a request to Codex and returns the final text output.

SendStream falls back to non-streaming (APIM gateway doesn't support SSE pass-through).

SetLastPRSync updates the timestamp of the last PR sync

SummarizeVersionContent takes raw version content and returns AI-enhanced summary

TranscribeFile transcribes the given audio file using the specified model. If the file exceeds the size limit, it can optionally be split into chunks

WalkCommitsSinceTag walks commits from the specified tag to HEAD and returns only "Unreleased" version

addFileToDirectory adds a file to the correct directory in the structure

buildChatCompletionParams builds parameters for the Chat Completions API

buildFabricChatURL constructs a valid HTTP/HTTPS base URL from various address formats. It accepts fully-qualified URLs (http:// or https://), :port s

buildMessageText combines chat messages into a single prompt for Copilot.

captureInput captures the input for a function call

checkImageGenerationCompatibility warns if the model doesn't support image generation

convertMessageCommon extracts common conversion logic

countPatternsInDirectory counts the number of pattern directories in a given directory

createConversation creates a new Copilot conversation.

Create a new pattern with necessary files and structure.

detectSystemLocale detects the system locale using standard Unix environment variables. Follows the POSIX priority order for locale environment variab