mirror of
https://github.com/openai/codex.git
synced 2026-11-20 22:40:37 +00:00
Let required hooks block continuation on failure (#62831)
## Why A required hook check can fail to run or return a usable result. Continuing after that failure can let an action proceed without a completed check. ## What changed Add per-handler `onFailure` for command and MCP tool hooks. The default `continue` preserves existing behavior. On supported synchronous hooks, `block` applies the event's blocking behavior and reports the reason while preserving failure diagnostics. For example, a failed `PreToolUse` check prevents the tool from running, while a failed `PostToolUse` check withholds the result of a tool that already ran. Expose the policy in the app-server's `configRequirements/read` response. ## Testing Add tests for command and MCP failures under both policies, and scenario coverage for blocked tool execution, withheld results, and completion after a `Stop` hook recovers. GitOrigin-RevId: 20d6ebda0094382fe052bbf34338edb994cc7bd3
This commit is contained in:
@@ -100,6 +100,7 @@ fn expected_source(index: usize) -> ExecutorPluginHookSource {
|
||||
.expect("executor hook input"),
|
||||
timeout_sec: None,
|
||||
status_message: None,
|
||||
on_failure: None,
|
||||
}],
|
||||
}],
|
||||
..Default::default()
|
||||
@@ -247,6 +248,7 @@ fn preserves_allowlisted_executor_plugin_hook_options() {
|
||||
.expect("manifest-provided executor hook input"),
|
||||
timeout_sec: Some(30),
|
||||
status_message: Some("Cleaning up Computer Use".to_string()),
|
||||
on_failure: None,
|
||||
};
|
||||
expected.hooks.interrupt = expected.hooks.stop.clone();
|
||||
|
||||
|
||||
Reference in New Issue
Block a user