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

@@ -186,6 +186,16 @@ pub enum Op {
/// Request to shut down codex instance.
Shutdown,
/// Execute a user-initiated one-off shell command (triggered by "!cmd").
///
/// The command string is executed using the user's default shell and may
/// include shell syntax (pipes, redirects, etc.). Output is streamed via
/// `ExecCommand*` events and the UI regains control upon `TaskComplete`.
RunUserShellCommand {
/// The raw command string after '!'
command: String,
},
}
/// Determines the conditions under which the user is consulted to approve
@@ -1086,6 +1096,10 @@ pub struct ExecCommandBeginEvent {
/// The command's working directory if not the default cwd for the agent.
pub cwd: PathBuf,
pub parsed_cmd: Vec<ParsedCommand>,
/// True when this exec was initiated directly by the user (e.g. bang command),
/// not by the agent/model. Defaults to false for backwards compatibility.
#[serde(default)]
pub is_user_shell_command: bool,
}
#[derive(Debug, Clone, Deserialize, Serialize, JsonSchema, TS)]