test(realtime): sample pending response events

Poll the event count during the held transcription instead of checking\na captured value. Document the client commit and response ordering.

Assisted-by: Codex:gpt-6
Signed-off-by: nexxtmobile.de <kai@nexxtmobile.de>
(cherry picked from commit 034086d3b0)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

core/http/endpoints/openai/realtime_client_commit_test.go

@@ -79,7 +79,9 @@ var _ = Describe("realtime client-commit LLM/STT ordering", func() {
 		// With the fix it WAITS for the held STT: no response is created while
 		// the transcription is in flight.
 		session.issueClientResponse(types.ResponseCreateParams{}, conv, tr)
-		Consistently(tr.countEvents(types.ServerEventTypeResponseCreated), 200*time.Millisecond).Should(BeZero())
+		Consistently(func() int {
+			return tr.countEvents(types.ServerEventTypeResponseCreated)
+		}, 200*time.Millisecond).Should(BeZero())
 
 		// Release the STT; the commit appends its user item and the waiting
 		// response now starts on the real transcript.

docs/content/features/openai-realtime.md

@@ -127,6 +127,11 @@ or set it to `true` to enable interruption again.
 
 ### Turn detection
 
+For client-controlled turns, set `turn_detection` to `null` in `session.update`.
+After sending audio, send `input_audio_buffer.commit`, followed by `response.create`.
+If transcription is still running, the response waits for the committed user item before starting the LLM.
+A standalone `response.create` with no pending client commit starts without this wait.
+
 Turn detection decides when the user has finished speaking and the pipeline should respond. Two modes are supported, matching the OpenAI session schema:
 
 - **`server_vad`** (default): silence-based. The VAD model watches the audio and the turn commits after `silence_duration_ms` (default 500 ms) of silence. Simple and model-agnostic, but a fixed silence window must trade interrupting mid-sentence pauses against sluggish responses.