TEN-framework / TEN-framework/ten-framework
[BUG] Unable to interact after successful link connection, realtime mode
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 11.1k
- Forks
- 1.4k
- Avg merge
- 2d 15m
- Merged PRs (30d)
- 22
Description
Description
Install according to the official tutorial
Enter the "voice-assistant-realtime" folder
Execute "task install"
Execute "task run"
The logs show that the voice interaction is working properly, but it doesn't actually respond on the page.
I checked the log history, and only this location showed an error.
[agora_ijcgf6] 2025-12-06T14:42:02.274676626+00:00 7818(7840) I key_point on_start@rtc_extension.cc:30 [agora_rtc_extension] config: {"agora_asr_full_config":"","agora_asr_hotwords":[],"agora_asr_language":"","agora_asr_session_control_file_path":"","agora_asr_shift_timestamp":false,"agora_asr_vendor_app_id":"","agora_asr_vendor_key":"","agora_asr_vendor_name":"","agora_asr_vendor_region":"","agora_asr_vendor_secret":"","agora_asr_vendor_uri":"","app_certificate":"519f****","app_id":"8254e7662b684723a263125822a49caf","area_code":-1,"audio_frame_send_delay_ms":100,"audio_scenario":0,"auto_join":true,"channel":"agora_ijcgf6","datastream_encryption_enabled":false,"enable_agora_asr":false,"enable_asr_log":false,"enable_string_uid":false,"encryption_key":"","encryption_mode":0,"encryption_salt":"","preload_asr_filters":[],"privilege_expire_seconds":86400,"publish_audio":true,"publish_audio_auto_publishing":true,"publish_data":true,"publish_video":false,"publish_video_auto_publishing":true,"publish_video_encoded":false,"publish_video_frame_rate":15,"publish_video_height":480,"publish_video_width":640,"remote_stream_id":149652,"remote_user_id":"","sdk_log_file_path":"","sdk_params":"","shift_audio_timestamp":false,"sid":"","stream_id":0,"subscribe_audio":true,"subscribe_audio_frame_source":"on_playback_before_mixing","subscribe_audio_num_of_channels":1,"subscribe_audio_sample_rate":16000,"subscribe_audio_samples_per_frame":0,"subscribe_remote_stream_ids":[149652],"subscribe_remote_user_ids":[],"subscribe_video":false,"subscribe_video_encoded":false,"subscribe_video_pix_fmt":0,"token":"007e****","token_expire_seconds":86400,"unsubscribe_remote_stream_ids":[],"unsubscribe_remote_user_ids":[],"use_frame_counted_audio_timestamp":false,"user_id":""}
[agora_ijcgf6] 2025-12-06T14:42:02.293558475+00:00 7818(7843) I ten:runtime ten_extension_handle_ten_namespace_properties@metadata.c:346 [v2v] ten section is not found in the property, skip
[agora_ijcgf6] 2025-12-06T14:42:02.299795067+00:00 7818(7843) W ten:runtime ten_metadata_flatten_manifest_api_definition@metadata.c:167 Failed to flatten manifest api definition: Failed to read content file from /app/agents/ten_packages/system/ten_ai_base/api/mllm-interface.json
[agora_ijcgf6] 2025-12-06T14:42:02.299829895+00:00 7818(7843) E ten:runtime ten_metadata_init_schema_store@metadata.c:209 Failed to flatten manifest api definition. base_dir: /app/agents/ten_packages/extension/openai_mllm_python, app_base_dir: /app/agents/examples/voice-assistant-realtime/tenapp
Environment
docker cpu
Steps to reproduce
Install according to the official tutorial, then start task run.
Expected behavior
Normal voice interaction
Severity
Critical
Additional Information
No response
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Reproduce the issue in examples/voice-assistant-realtime with task install and task run, then inspect the reported locations in rtc_extension.cc:30 and metadata.c:167-209. Check the missing ten_ai_base/api/mllm-interface.json content under the openai_mllm_python package and verify that the page responds normally after the metadata error is resolved.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- docker, python
- Domain
- ai, audio-video-rtc
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100