From 863a1bf177f7cc451c1c100488b121bb485882ee Mon Sep 17 00:00:00 2001 From: Paul Kompfner Date: Tue, 12 May 2026 16:04:12 -0400 Subject: [PATCH] Add changelog for #4474 --- changelog/4474.fixed.md | 1 + 1 file changed, 1 insertion(+) create mode 100644 changelog/4474.fixed.md diff --git a/changelog/4474.fixed.md b/changelog/4474.fixed.md new file mode 100644 index 000000000..bd6c1b50c --- /dev/null +++ b/changelog/4474.fixed.md @@ -0,0 +1 @@ +- Extended the `cancel_on_interruption=False` regression fix to `InworldRealtimeLLMService`. Uses the same approach as in #4441 (the service detects async-tool messages in the LLM context and routes the final result to its formal tool-result channel). Note: as of this writing, Inworld Realtime doesn't appear to handle the resulting delayed tool result reliably — the routing is best-effort and the service surfaces a one-time warning when async-tool messages are seen. Streamed intermediate results (`FunctionCallResultProperties(is_final=False)`) are still not supported on this realtime service. (Inworld was excluded from #4447 pending resolution of an unrelated tool-calling issue, which turned out to be an account-level matter.)