Struct MemoryRetainTool 

pub struct MemoryRetainTool;

Unstable (feature: memory) — may change or be removed

The `memory_*` + `subagent` tool structs (register directly if desired). Tool that persists a memory item (content, kind, importance) to the configured `MemoryBackend`.

Requires ctx.memory to be set; otherwise returns an error. The memory is scoped to the current session (ctx.session_id), falling back to "default" when no session id is available.

Trait Implementations

impl AgentTool for MemoryRetainTool

fn name(&self) -> &str

Tool name (used in function calls)

fn label(&self) -> &str

Human-readable label

fn description(&self) -> &str

Description for the model

fn essential(&self) -> bool

Whether this tool is essential (cannot be disabled). Essential tools: read, write, edit, bash, grep, find, ls Optional tools: web_search, github, subagent, etc.

fn parameters_schema(&self) -> Value

JSON Schema for parameters

fn execute<'life0, 'life1, 'life2, 'async_trait>( &'life0 self, _tool_call_id: &'life1 str, params: Value, _signal: Option<Receiver<()>>, ctx: &'life2 ToolContext, ) -> Pin<Box<dyn Future<Output = Result<AgentToolResult, String>> + Send + 'async_trait>>

where 'life0: 'async_trait, 'life1: 'async_trait, 'life2: 'async_trait, MemoryRetainTool: 'async_trait,

Execute the tool with the given tool call ID and parameters.

fn on_progress(&self, _callback: Arc<dyn Fn(String) + Sync + Send>)

Called with progress updates during execution. Tools can override this to emit streaming updates.

fn on_browse_progress( &self, _callback: Arc<dyn Fn(BrowseProgress) + Sync + Send>, )

Structured browse progress callback for browser tool context enrichment. Default implementation is no-op. Only browse tools override this to register a callback that enriches ToolCallContext with structured data from BrowseProgress events.

fn render_call(&self, _params: &Value) -> Option<RenderOutput>

Custom rendering for tool call (TUI visualization). Return None to use the default tool_renderer.rs formatter.

fn render_result(&self, _result: &AgentToolResult) -> Option<RenderOutput>

Custom rendering for tool result (TUI visualization). Return None to use the default tool_renderer.rs formatter.

fn intent(&self) -> Option<&str>

Intent trace — a concise description of what this tool does. Returned value is included in ToolExecutionStart / ToolExecutionEnd events so the agent loop can surface intent to users or telemetry. Default None (no intent tracing).

fn execution_mode(&self) -> ToolExecutionMode

Execution mode for parallel safety. Defaults to ParallelSafe. Override for file-mutating or sequential tools.

fn tool_tier(&self) -> ToolTier

Risk tier for approval gating.

fn current_tab_id(&self) -> Option<Uuid>

Return the current active tab ID, if this tool manages browser tabs. Defaults to None. Browser tools override this to return the tab ID of the currently-open tab during execution, so the agent loop can populate ToolExecutionUpdate.tab_id.

fn set_tab_id_slot(&self, _slot: Arc<Mutex<RawMutex, Option<Uuid>>>)

Receive a shared slot where the tool can write the current tab ID. The agent loop creates the slot and passes it before on_progress; the tool writes Some(tab_id) when it opens a tab and None when it closes it. Defaults to a no-op — only tab-aware tools override.

fn to_definition(&self) -> ToolDefinition

Convert to ToolDefinition