feat(agent): support multimodal intent input and ASR transcribe endpoint

2026-03-08 17:34:28 +08:00
parent 5ada60e834
commit 1060503a2d
11 changed files with 422 additions and 74 deletions
@@ -10,3 +10,7 @@ class TaskAcceptedResponse(BaseModel):
    thread_id: str = Field(alias="threadId")
    run_id: str = Field(alias="runId")
    created: bool
+
+
+class AsrTranscribeResponse(BaseModel):
+    transcript: str = Field(description="Transcribed text from audio")