audio and transcript

cht/agent/openai_compat_provider.py

@@ -95,10 +95,17 @@ class OpenAICompatProvider(AgentProvider):
 
         # Build context header
         m, s = divmod(int(context.duration), 60)
-        ctx_text = (
-            f"Recording duration: {m:02d}:{s:02d}\n"
-            f"Total frames: {len(context.frames)}\n"
-        )
+        ctx_lines = [
+            f"Recording duration: {m:02d}:{s:02d}",
+            f"Total frames: {len(context.frames)}",
+        ]
+        if context.transcript_segments:
+            ctx_lines.append(f"\nTranscript ({len(context.transcript_segments)} segments):")
+            for t in context.transcript_segments:
+                tm1, ts1 = divmod(int(t.start), 60)
+                tm2, ts2 = divmod(int(t.end), 60)
+                ctx_lines.append(f"  {t.id} [{tm1:02d}:{ts1:02d}-{tm2:02d}:{ts2:02d}] {t.text}")
+        ctx_text = "\n".join(ctx_lines) + "\n"
 
         frames_to_send = context.mentioned_frames