Files
codex/codex-rs/core/src/tools/parallel.rs
Owen Lin 5ea107a088 feat(app-server, core): allow text + image content items for dynamic tool outputs (#10567)
Took over the work that @aaronl-openai started here:
https://github.com/openai/codex/pull/10397

Now that app-server clients are able to set up custom tools (called
`dynamic_tools` in app-server), we should expose a way for clients to
pass in not just text, but also image outputs. This is something the
Responses API already supports for function call outputs, where you can
pass in either a string or an array of content outputs (text, image,
file):
https://platform.openai.com/docs/api-reference/responses/create#responses_create-input-input_item_list-item-function_tool_call_output-output-array-input_image

So let's just plumb it through in Codex (with the caveat that we only
support text and image for now). This is implemented end-to-end across
app-server v2 protocol types and core tool handling.

## Breaking API change
NOTE: This introduces a breaking change with dynamic tools, but I think
it's ok since this concept was only recently introduced
(https://github.com/openai/codex/pull/9539) and it's better to get the
API contract correct. I don't think there are any real consumers of this
yet (not even the Codex App).

Old shape:
`{ "output": "dynamic-ok", "success": true }`

New shape:
```
{
    "contentItems": [
      { "type": "inputText", "text": "dynamic-ok" },
      { "type": "inputImage", "imageUrl": "data:image/png;base64,AAA" }
    ]
  "success": true
}
```
2026-02-04 16:12:47 -08:00

139 lines
4.8 KiB
Rust

use std::sync::Arc;
use std::time::Instant;
use tokio::sync::RwLock;
use tokio_util::either::Either;
use tokio_util::sync::CancellationToken;
use tokio_util::task::AbortOnDropHandle;
use tracing::Instrument;
use tracing::instrument;
use tracing::trace_span;
use crate::codex::Session;
use crate::codex::TurnContext;
use crate::error::CodexErr;
use crate::function_tool::FunctionCallError;
use crate::tools::context::SharedTurnDiffTracker;
use crate::tools::context::ToolPayload;
use crate::tools::router::ToolCall;
use crate::tools::router::ToolRouter;
use codex_protocol::models::FunctionCallOutputBody;
use codex_protocol::models::FunctionCallOutputPayload;
use codex_protocol::models::ResponseInputItem;
#[derive(Clone)]
pub(crate) struct ToolCallRuntime {
router: Arc<ToolRouter>,
session: Arc<Session>,
turn_context: Arc<TurnContext>,
tracker: SharedTurnDiffTracker,
parallel_execution: Arc<RwLock<()>>,
}
impl ToolCallRuntime {
pub(crate) fn new(
router: Arc<ToolRouter>,
session: Arc<Session>,
turn_context: Arc<TurnContext>,
tracker: SharedTurnDiffTracker,
) -> Self {
Self {
router,
session,
turn_context,
tracker,
parallel_execution: Arc::new(RwLock::new(())),
}
}
#[instrument(level = "trace", skip_all, fields(call = ?call))]
pub(crate) fn handle_tool_call(
self,
call: ToolCall,
cancellation_token: CancellationToken,
) -> impl std::future::Future<Output = Result<ResponseInputItem, CodexErr>> {
let supports_parallel = self.router.tool_supports_parallel(&call.tool_name);
let router = Arc::clone(&self.router);
let session = Arc::clone(&self.session);
let turn = Arc::clone(&self.turn_context);
let tracker = Arc::clone(&self.tracker);
let lock = Arc::clone(&self.parallel_execution);
let started = Instant::now();
let dispatch_span = trace_span!(
"dispatch_tool_call",
otel.name = call.tool_name.as_str(),
tool_name = call.tool_name.as_str(),
call_id = call.call_id.as_str(),
aborted = false,
);
let handle: AbortOnDropHandle<Result<ResponseInputItem, FunctionCallError>> =
AbortOnDropHandle::new(tokio::spawn(async move {
tokio::select! {
_ = cancellation_token.cancelled() => {
let secs = started.elapsed().as_secs_f32().max(0.1);
dispatch_span.record("aborted", true);
Ok(Self::aborted_response(&call, secs))
},
res = async {
let _guard = if supports_parallel {
Either::Left(lock.read().await)
} else {
Either::Right(lock.write().await)
};
router
.dispatch_tool_call(session, turn, tracker, call.clone())
.instrument(dispatch_span.clone())
.await
} => res,
}
}));
async move {
match handle.await {
Ok(Ok(response)) => Ok(response),
Ok(Err(FunctionCallError::Fatal(message))) => Err(CodexErr::Fatal(message)),
Ok(Err(other)) => Err(CodexErr::Fatal(other.to_string())),
Err(err) => Err(CodexErr::Fatal(format!(
"tool task failed to receive: {err:?}"
))),
}
}
.in_current_span()
}
}
impl ToolCallRuntime {
fn aborted_response(call: &ToolCall, secs: f32) -> ResponseInputItem {
match &call.payload {
ToolPayload::Custom { .. } => ResponseInputItem::CustomToolCallOutput {
call_id: call.call_id.clone(),
output: Self::abort_message(call, secs),
},
ToolPayload::Mcp { .. } => ResponseInputItem::McpToolCallOutput {
call_id: call.call_id.clone(),
result: Err(Self::abort_message(call, secs)),
},
_ => ResponseInputItem::FunctionCallOutput {
call_id: call.call_id.clone(),
output: FunctionCallOutputPayload {
body: FunctionCallOutputBody::Text(Self::abort_message(call, secs)),
..Default::default()
},
},
}
}
fn abort_message(call: &ToolCall, secs: f32) -> String {
match call.tool_name.as_str() {
"shell" | "container.exec" | "local_shell" | "shell_command" | "unified_exec" => {
format!("Wall time: {secs:.1} seconds\naborted by user")
}
_ => format!("aborted by user after {secs:.1}s"),
}
}
}