Struct CompressedExecutor 

pub struct CompressedExecutor<E: ToolExecutor> { /* private fields */ }

Decorator that runs a compressor on each successful tool output.

The inner executor is called first; its output is then passed to compressor.compress. If compression returns Ok(None) or Err(...), the original summary is kept intact. Compression errors are logged as warnings but never propagate to the caller.

Type parameters

• E — the wrapped ToolExecutor. Often CompositeExecutor or DynExecutor.

Examples

use std::sync::Arc;
use zeph_tools::compression::{CompressedExecutor, IdentityCompressor};
// let executor = CompressedExecutor::new(inner_executor, Arc::new(IdentityCompressor), 200);

Implementations

impl<E: ToolExecutor> CompressedExecutor<E>

pub fn new( inner: E, compressor: Arc<dyn OutputCompressor>, min_lines: usize, ) -> Self

Wrap inner with compressor.

Outputs with fewer than min_lines lines skip the compressor entirely.

Trait Implementations

impl<E: Debug + ToolExecutor> Debug for CompressedExecutor<E>

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

Formats the value using the given formatter.

impl<E: ToolExecutor> ToolExecutor for CompressedExecutor<E>

async fn execute(&self, response: &str) -> Result<Option<ToolOutput>, ToolError>

Parse response for fenced tool blocks and execute them.

async fn execute_confirmed( &self, response: &str, ) -> Result<Option<ToolOutput>, ToolError>

Execute bypassing confirmation checks (called after user approves).

fn tool_definitions(&self) -> Vec<ToolDef>

Return the tool definitions this executor can handle.

async fn execute_tool_call( &self, call: &ToolCall, ) -> Result<Option<ToolOutput>, ToolError>

Execute a structured tool call. Returns Ok(None) if call.tool_id is not handled.

async fn execute_tool_call_confirmed( &self, call: &ToolCall, ) -> Result<Option<ToolOutput>, ToolError>

Execute a structured tool call bypassing confirmation checks.

fn set_skill_env(&self, env: Option<HashMap<String, String>>)

Inject environment variables for the currently active skill. No-op by default.

fn set_effective_trust(&self, level: SkillTrustLevel)

Set the effective trust level for the currently active skill. No-op by default.

fn is_tool_retryable(&self, tool_id: &str) -> bool

Whether the executor can safely retry this tool call on a transient error.

fn is_tool_speculatable(&self, tool_id: &str) -> bool

Whether a tool call can be safely dispatched speculatively (before the LLM finishes).

fn requires_confirmation(&self, _call: &ToolCall) -> bool

Return true when call would require user confirmation before execution.