[tool search] support namespaced deferred dynamic tools (#18413)

Deferred dynamic tools need to round-trip a namespace so a tool returned
by `tool_search` can be called through the same registry key that core
uses for dispatch.

This change adds namespace support for dynamic tool specs/calls,
persists it through app-server thread state, and routes dynamic tool
calls by full `ToolName` while still sending the app the leaf tool name.
Deferred dynamic tools must provide a namespace; non-deferred dynamic
tools may remain top-level.

It also introduces `LoadableToolSpec` as the shared
function-or-namespace Responses shape used by both `tool_search` output
and dynamic tool registration, so dynamic tools use the same wrapping
logic in both paths.

Validation:
- `cargo test -p codex-tools`
- `cargo test -p codex-core tool_search`

---------

Co-authored-by: Sayan Sisodiya <sayan@openai.com>
This commit is contained in:
pash-openai
2026-04-20 23:13:08 -07:00
committed by GitHub
parent 1dcea729d3
commit dc1a8f2190
60 changed files with 676 additions and 147 deletions

View File

@@ -127,6 +127,7 @@ async fn thread_unsubscribe_during_turn_keeps_turn_running() -> Result<()> {
.send_thread_start_request(ThreadStartParams {
model: Some("mock-model".to_string()),
dynamic_tools: Some(vec![DynamicToolSpec {
namespace: None,
name: tool_name.to_string(),
description: "Deterministic wait tool".to_string(),
input_schema: json!({
@@ -194,6 +195,7 @@ async fn thread_unsubscribe_during_turn_keeps_turn_running() -> Result<()> {
thread_id: thread_id.clone(),
turn_id: started.turn_id,
call_id: call_id.to_string(),
namespace: None,
tool: tool_name.to_string(),
arguments: tool_args,
}