wangweiandCopilot 7adc050968 feat: record streaming token usage in TrackedLLMClient.stream_chat ...

Implement manual generator driving using next()/StopIteration to capture
the return value (trailing usage dict) from inner stream_chat() implementations,
enabling token tracking for streaming LLM calls.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

2026-07-23 13:42:33 +08:00

..

__init__.py

Fix SSE route dependency and align architecture docs

2026-05-18 16:32:42 +08:00

base_client.py

Add LLM token

2026-07-02 22:03:39 +08:00

deepseek_client.py

feat: capture streaming token usage in DeepSeekClient.stream_chat

2026-07-23 11:24:31 +08:00

document_summarizer.py

Fix SSE route dependency and align architecture docs

2026-05-18 16:32:42 +08:00

llm_factory.py

feat: wrap LLM clients with TrackedLLMClient in LLMFactory

2026-07-02 15:03:12 +08:00

qwen_client.py

feat: capture streaming token usage in QwenClient and QwenVLClient

2026-07-23 13:19:23 +08:00

tool_types.py

Add LLM token

2026-07-02 22:03:39 +08:00

tracked_client.py

feat: record streaming token usage in TrackedLLMClient.stream_chat

2026-07-23 13:42:33 +08:00