feature: Add "!cmd" user shell execution (#2471)

feature: Add "!cmd" user shell execution

This change lets users run local shell commands directly from the TUI by
prefixing their input with ! (e.g. !ls). Output is truncated to keep the
exec cell usable, and Ctrl-C cleanly
  interrupts long-running commands (e.g. !sleep 10000).

**Summary of changes**

- Route Op::RunUserShellCommand through a dedicated UserShellCommandTask
(core/src/tasks/user_shell.rs), keeping the task logic out of codex.rs.
- Reuse the existing tool router: the task constructs a ToolCall for the
local_shell tool and relies on ShellHandler, so no manual MCP tool
lookup is required.
- Emit exec lifecycle events (ExecCommandBegin/ExecCommandEnd) so the
TUI can show command metadata, live output, and exit status.

**End-to-end flow**

  **TUI handling**

1. ChatWidget::submit_user_message (TUI) intercepts messages starting
with !.
2. Non-empty commands dispatch Op::RunUserShellCommand { command };
empty commands surface a help hint.
3. No UserInput items are created, so nothing is enqueued for the model.

  **Core submission loop**
4. The submission loop routes the op to handlers::run_user_shell_command
(core/src/codex.rs).
5. A fresh TurnContext is created and Session::spawn_user_shell_command
enqueues UserShellCommandTask.

  **Task execution**
6. UserShellCommandTask::run emits TaskStartedEvent, formats the
command, and prepares a ToolCall targeting local_shell.
  7. ToolCallRuntime::handle_tool_call dispatches to ShellHandler.

  **Shell tool runtime**
8. ShellHandler::run_exec_like launches the process via the unified exec
runtime, honoring sandbox and shell policies, and emits
ExecCommandBegin/End.
9. Stdout/stderr are captured for the UI, but the task does not turn the
resulting ToolOutput into a model response.

  **Completion**
10. After ExecCommandEnd, the task finishes without an assistant
message; the session marks it complete and the exec cell displays the
final output.

  **Conversation context**

- The command and its output never enter the conversation history or the
model prompt; the flow is local-only.
  - Only exec/task events are emitted for UI rendering.

**Demo video**


https://github.com/user-attachments/assets/fcd114b0-4304-4448-a367-a04c43e0b996
This commit is contained in:
Abhishek Bhardwaj
2025-10-29 00:31:20 -07:00
committed by GitHub
parent 802d2440b4
commit 89591e4246
16 changed files with 419 additions and 21 deletions

View File

@@ -1287,6 +1287,15 @@ async fn submission_loop(sess: Arc<Session>, config: Arc<Config>, rx_sub: Receiv
Op::Compact => {
handlers::compact(&sess, sub.id.clone()).await;
}
Op::RunUserShellCommand { command } => {
handlers::run_user_shell_command(
&sess,
sub.id.clone(),
command,
&mut previous_context,
)
.await;
}
Op::Shutdown => {
if handlers::shutdown(&sess, sub.id.clone()).await {
break;
@@ -1313,6 +1322,7 @@ mod handlers {
use crate::tasks::CompactTask;
use crate::tasks::RegularTask;
use crate::tasks::UndoTask;
use crate::tasks::UserShellCommandTask;
use codex_protocol::custom_prompts::CustomPrompt;
use codex_protocol::protocol::ErrorEvent;
use codex_protocol::protocol::Event;
@@ -1388,6 +1398,24 @@ mod handlers {
}
}
pub async fn run_user_shell_command(
sess: &Arc<Session>,
sub_id: String,
command: String,
previous_context: &mut Option<Arc<TurnContext>>,
) {
let turn_context = sess
.new_turn_with_sub_id(sub_id, SessionSettingsUpdate::default())
.await;
sess.spawn_task(
Arc::clone(&turn_context),
Vec::new(),
UserShellCommandTask::new(command),
)
.await;
*previous_context = Some(turn_context);
}
pub async fn exec_approval(sess: &Arc<Session>, id: String, decision: ReviewDecision) {
match decision {
ReviewDecision::Abort => {