From 586d0de244e10d28e390dc880f18a32a9c6e597b Mon Sep 17 00:00:00 2001
From: klopez4212 <klopez4212@gmail.com>
Date: Sun, 5 Jul 2026 08:12:56 +0100
Subject: [PATCH] =?UTF-8?q?fix:=20address=20review=20comments=20=E2=80=94?=
 =?UTF-8?q?=20nested=20audio=20schema,=20item=20separators,=20safe=20auto-?=
 =?UTF-8?q?submit=20clear?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

- Relay: restructure OpenAI client-secrets payload to use the current
  typed transcription schema (audio.input.transcription) instead of the
  deprecated top-level input_audio_transcription field.
- realtimeAudio: insert space separators between transcript items when
  neither the preceding nor following text has whitespace, preventing
  multi-utterance runs from merging into unreadable text.
- useDictation: remove premature setText('') after auto-submit — the
  send flow handles clearing on success, so dictated text survives if a
  mention dialog opens or the send is blocked.

Signed-off-by: klopez4212 <klopez4212@gmail.com>
---
 crates/buzz-relay/src/api/transcribe.rs          | 16 +++++++++-------
 .../src/features/dictation/hooks/useDictation.ts |  7 ++++++-
 .../src/features/dictation/lib/realtimeAudio.ts  | 15 +++++++--------
 3 files changed, 22 insertions(+), 16 deletions(-)

diff --git a/crates/buzz-relay/src/api/transcribe.rs b/crates/buzz-relay/src/api/transcribe.rs
index f66c584e4..97263a87f 100644
--- a/crates/buzz-relay/src/api/transcribe.rs
+++ b/crates/buzz-relay/src/api/transcribe.rs
@@ -81,14 +81,16 @@ pub async fn create_transcribe_session(
         .header("Authorization", format!("Bearer {api_key}"))
         .header("Content-Type", "application/json")
         .json(&serde_json::json!({
-            "session": {
-                "type": "transcription",
-                "input_audio_transcription": {
-                    "model": model,
-                },
-                "turn_detection": {
-                    "type": "server_vad",
+            "type": "transcription",
+            "audio": {
+                "input": {
+                    "transcription": {
+                        "model": model,
+                    }
                 }
+            },
+            "turn_detection": {
+                "type": "server_vad",
             }
         }))
         .timeout(std::time::Duration::from_secs(10))
diff --git a/desktop/src/features/dictation/hooks/useDictation.ts b/desktop/src/features/dictation/hooks/useDictation.ts
index ad42ef569..5e21fed16 100644
--- a/desktop/src/features/dictation/hooks/useDictation.ts
+++ b/desktop/src/features/dictation/hooks/useDictation.ts
@@ -63,8 +63,13 @@ export function useDictation({
         return;
       }
 
+      // Set the text first so the composer shows the final dictated content,
+      // then trigger send. We intentionally do NOT clear the composer here —
+      // the send flow in MessageComposer handles clearing on successful send.
+      // If a mention dialog opens (non-member mention), the text stays in the
+      // composer so the user doesn't lose their dictated message.
+      setText(textWithoutPhrase.trim());
       onSend(textWithoutPhrase.trim());
-      setText("");
       lastTranscriptRef.current = "";
     },
     [autoSubmitPhrases, getText, onSend, isSendBlockedRef, setText],
diff --git a/desktop/src/features/dictation/lib/realtimeAudio.ts b/desktop/src/features/dictation/lib/realtimeAudio.ts
index 4aaaeb148..2ad6e010d 100644
--- a/desktop/src/features/dictation/lib/realtimeAudio.ts
+++ b/desktop/src/features/dictation/lib/realtimeAudio.ts
@@ -89,7 +89,12 @@ export function getTranscriptText(state: TranscriptSegmentState): string {
   for (const id of state.itemOrder) {
     const seg = state.items.get(id);
     if (!seg) continue;
-    result += seg.finalized ?? seg.pending;
+    const text = seg.finalized ?? seg.pending;
+    if (!text) continue;
+    if (result && !result.endsWith(" ") && !text.startsWith(" ")) {
+      result += " ";
+    }
+    result += text;
   }
   return result;
 }
@@ -136,13 +141,7 @@ export function mergeTranscriptEvent(
   }
 
   // Reconstruct full text from all items in order.
-  let result = "";
-  for (const id of state.itemOrder) {
-    const seg = state.items.get(id);
-    if (!seg) continue;
-    result += seg.finalized ?? seg.pending;
-  }
-  return result;
+  return getTranscriptText(state);
 }
 
 // ── Audio buffer capture ──────────────────────────────────────────────────