AuthHeader returns the Azure OpenAI auth header

BuildEndpoint constructs the full API endpoint URL for the given model

BuildEndpoint constructs the Vertex AI API endpoint URL Uses /publishers/google/models/{model}:generateContent path per Azure APIM Gateway routing Thi

BuildResponseParams exposes the shared Responses API request builder so auth-specialized vendors can reuse Fabric's OpenAI-compatible request shape.

CommitChanges creates a commit with the given message Uses native git CLI instead of go-git to properly handle worktree scenarios

CommitExists checks if a commit already exists in the cache

CreateAudioOutputFile creates a binary file for audio data

CreateClient creates a new client for a provider by name

CreateNewChangelogEntry aggregates all incoming PR files for release and includes direct commits

CustomHelpHandler handles help output with translations

DirectlyGetModels is used to fetch models directly from the API when the standard OpenAI SDK method fails due to a nonstandard format.

ExtractCitations extracts web citations from grounding metadata.

ExtractText exposes the shared Responses API text extraction logic so other vendors can reuse Fabric's response formatting and citation handling.

FetchAllMergedPRs fetches all merged PRs using GitHub's search API This is much more efficient than fetching PRs individually

FetchAllMergedPRsGraphQL fetches all merged PRs with their commits using GraphQL This is the ultimate optimization - gets everything in ~5-10 API call

FetchAndSavePlaylist fetches all videos in a playlist and saves them to a CSV file.

GetDefaultConfigPath returns the default path for the configuration file if it exists, otherwise returns an empty string.

GetLastPRSync returns the timestamp of the last PR sync

Helper methods for Config access

GetPRValidationDetails fetches only the data needed for validation (lightweight).

GetShowEpisodes retrieves episodes for a given show.

GetStatusDetails returns a detailed status of the working directory Uses native git CLI instead of go-git to properly handle worktree scenarios

GetUnreleasedContentHash returns the cached content hash for Unreleased

IsAudioFormat checks if the filename suggests an audio format

IsConfigured returns true if both gateway URL and subscription key are configured

Helper function to check if a symlink points to a directory

IsValidGeminiVoice checks if a voice name is valid

IsWorkingDirectoryClean checks if the working directory has any uncommitted changes Uses native git CLI instead of go-git to properly handle worktree

LevelFromInt converts an int to a Level.

ListGeminiVoices formats the voice list for display

ListModels returns the list of available Bedrock inference profiles

ListModels delegates to the active backend

ListModels returns the list of Gemini models available through Vertex AI

ListModels returns the list of models available through Azure OpenAI. These are deployment names that must exist in your Azure OpenAI resource.

ListStrategies prints available strategies

LoadEnvSettings copies non-empty Codex token values from env.

NewClient creates a new Microsoft 365 Copilot client.

NewClientCompatible creates a new LM Studio client with custom configuration.

NewStrategiesHandler registers the /strategies GET endpoint

NewTranslatedHelpWriter creates a new help writer with translations

NormalizeMessages remove empty messages and ensure messages order user-assist-user

ParseResponse parses the HTTP response body into text content

PersistPatterns copies custom patterns to the updated patterns directory

PopulateDB downloads strategies from the internet and populates the strategies folder

PrepareRequest prepares the HTTP request body for this backend's API format

PrepareRequest converts messages to Azure OpenAI (OpenAI-compatible) API format