Skip to main content

Class: MemoryDeleteTool

Defined in: packages/agentos/src/cognition/memory/io/tools/MemoryDeleteTool.ts:74

ITool implementation that soft-deletes a memory trace from the agent's SQLite brain database.

Usage:

const tool = new MemoryDeleteTool(brain);
const result = await tool.execute(
{ traceId: 'mt_3f2b8c1e-5d4a-4e6f-9b7c-2a1d0e8f6c5b', reason: 'Information is outdated.' },
context,
);
// result.output.deleted → true

Implements​

  • ITool<MemoryDeleteInput, MemoryDeleteOutput>

Constructors​

Constructor​

new MemoryDeleteTool(brain, writeBack?): MemoryDeleteTool

Defined in: packages/agentos/src/cognition/memory/io/tools/MemoryDeleteTool.ts:118

Parameters​

brain​

Brain

The agent's shared SQLite brain database connection.

writeBack?​

MemoryToolWriteBack

The facade that made the tool (Memory.createTools()): a deleted trace's knowledge-graph copy is deleted through it, and a delete a learning layer does not keep is taken back through it. Without it the tool restores the row itself.

Returns​

MemoryDeleteTool

Properties​

category​

readonly category: "memory" = 'memory'

Defined in: packages/agentos/src/cognition/memory/io/tools/MemoryDeleteTool.ts:91

Logical category for discovery and grouping.

Implementation of​

ITool.category


description​

readonly description: string

Defined in: packages/agentos/src/cognition/memory/io/tools/MemoryDeleteTool.ts:85

LLM-facing description.

Implementation of​

ITool.description


displayName​

readonly displayName: "Delete Memory" = 'Delete Memory'

Defined in: packages/agentos/src/cognition/memory/io/tools/MemoryDeleteTool.ts:82

Human-readable display name.

Implementation of​

ITool.displayName


hasSideEffects​

readonly hasSideEffects: true = true

Defined in: packages/agentos/src/cognition/memory/io/tools/MemoryDeleteTool.ts:94

This tool writes to the database.

Implementation of​

ITool.hasSideEffects


id​

readonly id: "memory-delete-v1" = 'memory-delete-v1'

Defined in: packages/agentos/src/cognition/memory/io/tools/MemoryDeleteTool.ts:76

Globally unique tool identifier.

Implementation of​

ITool.id


inputSchema​

readonly inputSchema: JSONSchemaObject

Defined in: packages/agentos/src/cognition/memory/io/tools/MemoryDeleteTool.ts:97

JSON schema for input validation and LLM tool-call construction.

Implementation of​

ITool.inputSchema


name​

readonly name: "memory_delete" = 'memory_delete'

Defined in: packages/agentos/src/cognition/memory/io/tools/MemoryDeleteTool.ts:79

LLM-facing tool name.

Implementation of​

ITool.name

Methods​

execute()​

execute(args, context): Promise<ToolExecutionResult<MemoryDeleteOutput>>

Defined in: packages/agentos/src/cognition/memory/io/tools/MemoryDeleteTool.ts:162

Set deleted = 1 on the memory trace matching traceId.

The WHERE clause filters to deleted = 0 so that attempting to delete an already-deleted trace returns { deleted: false } rather than silently succeeding — this gives callers accurate feedback.

The trace's knowledge-graph copy (the episodic record a memory manager on the same Brain writes of each trace it stores) is deleted with it, through the facade that made the tool.

Parameters​

args​

MemoryDeleteInput

Delete input (traceId, optional reason).

context​

ToolExecutionContext

Tool execution context; where it carries the turn's scope ids, the call reaches only a live trace of the turn's own scopes that the turn's own user filed (another scope's reads as not found, another user's is refused, other_user), and the delete runs through the learner session's recorder, deleting only while the trace holds what was read (conflict otherwise). Only a freeze stops a delete, with a layer or without one (frozen).

Returns​

Promise<ToolExecutionResult<MemoryDeleteOutput>>

{ deleted } status, or an error result.

Implementation of​

ITool.execute


refusalBeforeApproval()​

refusalBeforeApproval(_args, context): ToolExecutionResult<MemoryDeleteOutput> | undefined

Defined in: packages/agentos/src/cognition/memory/io/tools/MemoryDeleteTool.ts:137

The refusal a delete meets whatever a human would answer, read before the tool orchestrator's approval gate (ITool.refusalBeforeApproval), so no one is asked to approve a write that cannot act: a freeze, and, with the turn's scope ids on the call, a session that records no writes. A refusal that reads the trace (other_user, conflict) is given when the call runs. execute refuses the same call itself, in the same order.

Parameters​

_args​

Record<string, any>

The call's arguments, before the input schema is checked.

context​

ToolExecutionContext

The call's context.

Returns​

ToolExecutionResult<MemoryDeleteOutput> | undefined

The refusal, or undefined when the call may run.

Implementation of​

ITool.refusalBeforeApproval