mirror of
https://github.com/openai/codex.git
synced 2026-11-17 14:58:36 +00:00
feat(app-server): add ThreadItem::DynamicToolCall (#12732)
Previously, clients would call `thread/start` with dynamic_tools set, and when a model invokes a dynamic tool, it would just make the server->client `item/tool/call` request and wait for the client's response to complete the tool call. This works, but it doesn't have an `item/started` or `item/completed` event. Now we are doing this: - [new] emit `item/started` with `DynamicToolCall` populated with the call arguments - send an `item/tool/call` server request - [new] once the client responds, emit `item/completed` with `DynamicToolCall` populated with the response. Also, with `persistExtendedHistory: true`, dynamic tool calls are now reconstructable in `thread/read` and `thread/resume` as `ThreadItem::DynamicToolCall`.
This commit is contained in:
1 parent
73eaebbd1c
commit
a0fd94bde6
37 files changed
+2436
-113
No files matched your search
@@ -854,6 +854,7 @@ impl EventProcessor for EventProcessorWithHumanOutput {
|
||||
| EventMsg::RealtimeConversationRealtime(_)
|
||||
| EventMsg::RealtimeConversationClosed(_)
|
||||
| EventMsg::DynamicToolCallRequest(_)
|
||||
| EventMsg::DynamicToolCallResponse(_)
|
||||
| EventMsg::SkillRequestApproval(_) => {}
|
||||
}
|
||||
CodexStatus::Running
|
||||
@@ -925,6 +926,7 @@ impl EventProcessorWithHumanOutput {
|
||||
| EventMsg::ThreadRolledBack(_)
|
||||
| EventMsg::RequestUserInput(_)
|
||||
| EventMsg::DynamicToolCallRequest(_)
|
||||
| EventMsg::DynamicToolCallResponse(_)
|
||||
)
|
||||
}
|
||||
|
||||
|
||||
Reference in new issue
Block a user