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
@
2026-06-03 16:58:35 +08:00
2026-07-02 22:03:39 +08:00
@
2026-06-03 16:58:35 +08:00
2026-06-05 18:00:31 +08:00
2026-07-02 22:03:39 +08:00
2026-07-02 22:03:39 +08:00
2026-07-02 22:03:39 +08:00
@
2026-06-03 16:58:35 +08:00
@
2026-06-03 16:58:35 +08:00
@
2026-06-03 16:58:35 +08:00
@
2026-06-03 16:58:35 +08:00
@
2026-06-03 16:58:35 +08:00
2026-06-05 18:00:31 +08:00
2026-06-05 18:00:31 +08:00
2026-04-28 11:29:33 +08:00
2026-04-28 11:29:33 +08:00
2026-07-02 22:03:39 +08:00
2026-04-28 11:29:33 +08:00
2026-04-28 11:29:33 +08:00
2026-05-26 12:34:12 +08:00
S
Description
AIRegulation-DocAnalysis-Demo
12 MiB
Languages
Python 55.2%
HTML 22.7%
TypeScript 16.2%
CSS 2.8%
Shell 1.4%
Other 1.6%