fix(tools): enforce a disabled run_in_background at execution time (review findings)

enableRunInBackground: false removed the parameter from the advertised
schema only — the arg validator deliberately allows undeclared keys, so
a caller (or a model that has seen the parameter elsewhere) could still
force run_in_background: true and start background work past the
deployment's opt-out, in both tool-bash and tool-subagent. Both
producers now refuse the forced key loud in execute(); tests pin the
refusal (and that nothing spawns) alongside the untouched foreground
path; the schema-omission-is-advertising rule is recorded in the
runtime RFC and both READMEs.
This commit is contained in:
Yichen Jiang
2026-07-09 23:37:51 +08:00
parent 3ad561862f
commit 35acd34fd9
7 files changed
+41 -3

No files matched your search

+1 -1
View File
@@ -10,7 +10,7 @@ The plugin also contributes the `tool:bash` prompt section (order 105) — the c
| key | default | meaning |
|---|---|---|
| `enableRunInBackground` | `true` | Expose `run_in_background` in the schema. Disabled, the parameter is absent entirely (schema and capability never disagree) and the description says background execution is unavailable. |
| `enableRunInBackground` | `true` | Expose `run_in_background` in the schema. Disabled, the parameter is absent entirely (schema and capability never disagree), the description says background execution is unavailable, and a caller that forces the key anyway is refused at execution time (the arg validator allows undeclared keys, so the schema omission alone is not enforcement). |
## The `bash` tool
+7
View File
@@ -350,6 +350,13 @@ export function apply(ctx: Context, config: Config): void {
...args.timeoutMs !== undefined ? { timeoutMs: args.timeoutMs } : {},
}
if (args.run_in_background === true) {
// The schema omission is advertising, not enforcement — the arg
// validator deliberately allows undeclared keys, so a caller (or a
// model that has seen the parameter elsewhere) can still send it.
// A disabled deployment must refuse at execution time, loud.
if (!backgroundEnabled) {
throw new Error('run_in_background is disabled for this deployment (enableRunInBackground: false)')
}
// The generic runtime owns everything task-shaped; without it a task
// id would be uncollectable — fail loud with the fix, not a dangle.
const tasks = ctx.get('tasks')
@@ -408,6 +408,15 @@ describe('background execution through the task runtime', () => {
// The registry-held definition agrees (schema and capability never disagree).
const parameters = ctx.tools.get('bash')!.parameters as { properties: Record<string, unknown> }
expect('run_in_background' in parameters.properties).toBe(false)
// Schema omission is advertising, not enforcement: the arg validator
// allows undeclared keys, so a forced run_in_background must be REFUSED
// at execution time (review finding) — while foreground still works.
const forced = await call(ctx, 'bash', { command: 'echo hi', description: 'test command', run_in_background: true })
expect(forced.isError).toBe(true)
expect(text(forced)).toContain('run_in_background is disabled for this deployment')
const foreground = await call(ctx, 'bash', { command: 'echo hi', description: 'test command' })
expect(foreground.isError).toBe(false)
})
})