Xin Wang
|
e7a8cb1faa
|
Enhance text stream processing by adding synchronization for interrupted assistant turns. Introduce sync_streamed_assistant_context to align LLM context with UI text, and modify ProductTextStreamProcessor to handle interrupted text. Update pipeline to utilize the new functionality for managing assistant turn interruptions.
|
2026-05-26 08:33:02 +08:00 |
|
Xin Wang
|
2edcb51805
|
Add chat_id, variables, detail, timeout_sec, and send_system_prompt to LLMConfig; update create_llm_service to accept new parameters and handle FastGPT integration. Modify pipeline to utilize chat_id and adjust message handling based on provider settings.
|
2026-05-25 08:45:30 +08:00 |
|
Xin Wang
|
f301af396d
|
Update AGENTS.md with additional context on implementation and modify pipeline.py to include assistant aggregator in the processing flow.
|
2026-05-24 21:37:54 +08:00 |
|
Xin Wang
|
02db9545f0
|
fix text input no context update
|
2026-05-22 21:30:54 +08:00 |
|
Xin Wang
|
75a34bf071
|
Add gated turn start strategy
|
2026-05-22 13:36:47 +08:00 |
|
Xin Wang
|
872b8ac64a
|
move vad config to json
|
2026-05-21 17:23:04 +08:00 |
|
Xin Wang
|
b09ca18cb9
|
update bugs
|
2026-05-21 16:52:42 +08:00 |
|
Xin Wang
|
404381c818
|
Add xfyun asr service
|
2026-05-21 15:42:49 +08:00 |
|
Xin Wang
|
53d2f5233d
|
first vesion
|
2026-05-21 13:08:40 +08:00 |
|