local_exec_and_triage
Execute allow-listed test, build, typecheck, or lint commands and scrub verbose output into a concise digest of exit codes, failing tests, file locations, and stack traces.
Instructions
Execute allow-listed test, build, typecheck, or lint commands (pytest, npm test, npx tsc, cargo check, go test) in a managed subprocess with Windows process-tree kill protection (taskkill /T /F) and scrub verbose output on the Local GPU (0x cloud quota). WHEN TO USE: Running any test suite, compiler check, or linter that may produce >40 lines of noisy output. DO NOT USE FOR: Chained shell commands (&&, ;, | are blocked) or file edits. RETURNS: Full output directly if <=40 lines; otherwise a Local GPU-scrubbed digest containing only exit code, failing test names, <file>:<line> locations, and isolated stack traces.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"command": "<command>",
"working_dir": "<working_dir>"
},
"name": "local_exec_and_triage"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| command | Yes | Single allow-listed test/build/lint command line without chaining operators (e.g. "pytest", "npm test", "npx tsc --noEmit", "cargo check"). | |
| timeout_ms | No | Optional subprocess timeout in milliseconds (default 120000). | |
| working_dir | Yes | Working directory path for command execution. |