fix(tts): preserve legacy tool voice hints

This commit is contained in:
Peter Steinberger
2026-04-25 17:56:28 +01:00
parent dc7c703425
commit 60f9358348
5 changed files with 67 additions and 1 deletions

View File

@@ -14,6 +14,7 @@ Assistant output can carry a small set of delivery/render directives:
- `[embed ...]` for Control UI rich rendering
These directives are separate. `MEDIA:` and reply/voice tags remain delivery metadata; `[embed ...]` is the web-only rich render path.
Trusted tool-result media uses the same `MEDIA:` / `[[audio_as_voice]]` parser before delivery, so legacy tool outputs can still mark an audio attachment as a voice note.
When block streaming is enabled, `MEDIA:` remains single-delivery metadata for a
turn. If the same media URL is sent in a streamed block and repeated in the final