get_working_context
Retrieve top working-memory entries rendered as compact markdown, giving coding agents the essential current context needed to maintain consistency across sessions while minimizing token overhead.
Instructions
v3.1.0 M2: Compact markdown rendering of the top working-memory entries for ReAct-loop injection. Returns {markdown, entries, count}. Capped at ~150 tokens of output (entries truncated at 120 chars each).
Tool call template
This tool declares no required parameters. Add optional parameters from the input schema as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {},
"name": "get_working_context"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| top_k | No | Max entries to include (default 5) |