Struct IrisAgentService 

pub struct IrisAgentService { /* private fields */ }

High-level service for executing agent tasks with structured context.

This is the primary interface for all agent-based operations in git-iris. It handles:

• Configuration management
• Agent lifecycle
• Task context validation and formatting
• Environment validation

Example

let service = IrisAgentService::from_common_params(&params, None)?;
let context = TaskContext::for_gen();
let result = service.execute_task("commit", context).await?;

Implementations

impl IrisAgentService

pub fn new( config: Config, provider: String, model: String, fast_model: String, ) -> Self

Create a new service with explicit provider configuration

pub fn from_common_params( common_params: &CommonParams, repository_url: Option<String>, ) -> Result<Self>

Create service from common CLI parameters

This is the primary constructor for CLI usage. It:

• Loads and applies configuration
• Sets up the git repository (local or remote)
• Validates the environment

Errors

Returns an error when config loading, agent backend resolution, or repository setup fails.

pub fn check_environment(&self) -> Result<()>

Check that the environment is properly configured

Errors

Returns an error when the active provider configuration is incomplete.

pub async fn execute_task( &self, capability: &str, context: TaskContext, ) -> Result<StructuredResponse>

Execute an agent task with structured context

Arguments

• capability - The capability to invoke (e.g., “commit”, “review”, “pr”)
• context - Structured context describing what to analyze

Returns

The structured response from the agent

Errors

Returns an error when agent construction or task execution fails.

pub async fn execute_task_with_prompt( &self, capability: &str, task_prompt: &str, ) -> Result<StructuredResponse>

Execute a task with a custom prompt (for backwards compatibility)

Errors

Returns an error when agent construction or task execution fails.

pub async fn execute_task_with_style( &self, capability: &str, context: TaskContext, preset: Option<&str>, use_gitmoji: Option<bool>, instructions: Option<&str>, ) -> Result<StructuredResponse>

Execute an agent task with style overrides

Allows runtime override of preset and gitmoji settings without modifying the underlying config. Useful for UI flows where the user can change settings per-invocation.

Arguments

• capability - The capability to invoke
• context - Structured context describing what to analyze
• preset - Optional preset name override (e.g., “conventional”, “cosmic”)
• use_gitmoji - Optional gitmoji setting override
• instructions - Optional custom instructions from the user

Errors

Returns an error when agent construction or task execution fails.

pub async fn execute_chat_with_updates( &self, task_prompt: &str, content_update_sender: ContentUpdateSender, ) -> Result<StructuredResponse>

Execute a chat task with content update capabilities

This is used by Studio to enable Iris to update content via tool calls.

Errors

Returns an error when agent construction or chat execution fails.

pub async fn execute_chat_streaming<F>( &self, task_prompt: &str, content_update_sender: ContentUpdateSender, on_chunk: F, ) -> Result<StructuredResponse>

where F: FnMut(&str, &str) + Send,

Execute a chat task with streaming and content update capabilities

Combines streaming output with tool-based content updates for the TUI chat.

Errors

Returns an error when agent construction or chat streaming fails.

pub async fn execute_task_streaming<F>( &self, capability: &str, context: TaskContext, on_chunk: F, ) -> Result<StructuredResponse>

where F: FnMut(&str, &str) + Send,

Execute an agent task with streaming

This method streams LLM output in real-time, calling the callback with each text chunk as it arrives. Ideal for TUI display of generation progress.

Arguments

• capability - The capability to invoke (e.g., “review”, “pr”, “changelog”)
• context - Structured context describing what to analyze
• on_chunk - Callback receiving (chunk, aggregated_text) for each delta

Returns

The final structured response after streaming completes

Errors

Returns an error when agent construction or streaming execution fails.

pub fn config(&self) -> &Config

Get the configuration

pub fn config_mut(&mut self) -> &mut Config

Get a mutable reference to the configuration

pub fn set_git_repo(&mut self, repo: GitRepo)

Attach a git repository to this service

pub fn git_repo(&self) -> Option<&Arc<GitRepo>>

Get the git repository if available

pub fn provider(&self) -> &str

Get the provider name

pub fn model(&self) -> &str

Get the model name

pub fn fast_model(&self) -> &str

Get the fast model name (for subagents and simple tasks)

pub fn api_key(&self) -> Option<String>

Get the API key for the current provider from config