Struct TurnToolLimitMiddleware 

pub struct TurnToolLimitMiddleware { /* private fields */ }

Middleware that enforces a hard limit on tool calls per turn.

Mounted on on_post_llm hook. When the turn’s tool call count reaches max_tool_calls_per_turn, this middleware:

1. Clears ctx.tool_calls (discards pending tool calls)
2. Injects a follow_up_message forcing the LLM to summarize

This is a hard constraint — unlike prompt rules, the model cannot bypass it.

Implementations

impl TurnToolLimitMiddleware

pub fn new(max_tool_calls_per_turn: usize) -> Self

pub fn from_config(config: &SafetyConfig) -> Self

Trait Implementations

impl Middleware for TurnToolLimitMiddleware

fn on_post_llm<'life0, 'life1, 'async_trait>( &'life0 self, ctx: &'life1 mut PostLlmCtx, ) -> Pin<Box<dyn Future<Output = AgentResult<()>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait, 'life1: 'async_trait,

fn on_user_message<'life0, 'life1, 'async_trait>( &'life0 self, _ctx: &'life1 mut UserMessageCtx, ) -> Pin<Box<dyn Future<Output = AgentResult<()>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait, 'life1: 'async_trait,

fn on_pre_llm<'life0, 'life1, 'async_trait>( &'life0 self, _ctx: &'life1 mut PreLlmCtx, ) -> Pin<Box<dyn Future<Output = AgentResult<()>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait, 'life1: 'async_trait,