Struct ToolLoopHandle 

pub struct ToolLoopHandle<'a, Ctx: LoopDepth + Send + Sync + 'static> { /* private fields */ }

Caller-driven resumable tool loop.

Unlike tool_loop which runs autonomously, this struct gives the caller control between each tool execution round. Call next_turn() to advance the loop, inspect the result, then consume the Yielded handle to control what happens next.

No spawning required

This is a direct state machine — no background tasks, no channels. The caller drives it by calling next_turn() which performs one iteration (LLM call + tool execution) and returns.

Lifecycle

1. Create with new()
2. Call next_turn() to get the first result
3. If Yielded, consume via resume() / continue_loop() / etc., then call next_turn() again
4. Repeat until Completed or Error
5. Optionally call into_result() for a ToolLoopResult

Implementations

impl<'a, Ctx: LoopDepth + Send + Sync + 'static> ToolLoopHandle<'a, Ctx>

pub fn new( provider: &'a dyn DynProvider, registry: &'a ToolRegistry<Ctx>, params: ChatParams, config: ToolLoopConfig, ctx: &Ctx, ) -> Self

Create a new resumable tool loop.

Does not start execution — call next_turn() to begin the first iteration.

Depth Tracking

Same as tool_loop — if Ctx implements LoopDepth, nested calls are tracked and max_depth is enforced. If the depth limit is already exceeded, the first call to next_turn() returns Error.

pub async fn next_turn(&mut self) -> TurnResult<'a, '_, Ctx>

Advance the loop and return the result of this turn.

Each call performs one iteration: LLM generation, tool execution (if applicable), and returns the result.

Returns a TurnResult that must be matched:

• TurnResult::Yielded — tools ran, consume via resume() / continue_loop() / inject_and_continue() / stop() to continue
• TurnResult::Completed — loop is done, read .response
• TurnResult::Error — loop failed, read .error

After Completed or Error, all subsequent calls return the same terminal result.

pub fn resume(&mut self, command: LoopCommand)

Tell the loop how to proceed before the next next_turn() call.

When using TurnResult::Yielded, prefer the convenience methods on Yielded (continue_loop(), inject_and_continue(), stop()), which consume the yielded handle and call this internally.

This method is useful when you need to set a command on the handle directly — for example, when driving the handle from an external event loop that receives the command asynchronously after the Yielded has already been consumed.

Has no effect after Completed or Error.

pub fn messages(&self) -> &[ChatMessage]

Get a snapshot of the current conversation messages.

Useful for context window management or debugging.

pub fn messages_mut(&mut self) -> &mut Vec<ChatMessage>

Get a mutable reference to the conversation messages.

Allows direct manipulation of the message history between iterations (e.g., for context compaction/summarization).

pub fn total_usage(&self) -> &Usage

Get the accumulated usage across all iterations so far.

pub fn iterations(&self) -> u32

Get the current iteration count.

pub fn is_finished(&self) -> bool

Whether the loop has finished (returned Completed or Error).

pub fn into_result(self) -> ToolLoopResult

Consume the handle and return a ToolLoopResult.

If the loop hasn’t completed yet, returns a result with current iteration count and TerminationReason::Complete.

Trait Implementations

impl<Ctx: LoopDepth + Send + Sync + 'static> Debug for ToolLoopHandle<'_, Ctx>

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.