wangwei and Copilot
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
wangwei and Copilot
f2bd0deeb3
feat: capture streaming token usage in QwenClient and QwenVLClient
...
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com >
2026-07-23 13:19:23 +08:00
wangwei and Copilot
81a6d54fff
feat: capture streaming token usage in DeepSeekClient.stream_chat
...
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com >
2026-07-23 11:24:31 +08:00
wangwei and Copilot
66fc388bfb
feat: record reranker call outcome into ModelUsageTracker
...
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com >
2026-07-02 15:42:20 +08:00
wangwei
41096369d3
feat: record embedding call usage into ModelUsageTracker
2026-07-02 15:15:03 +08:00
wangwei
4fea159f5b
feat: wrap LLM clients with TrackedLLMClient in LLMFactory
2026-07-02 15:03:12 +08:00
wangwei and Copilot
d460397dda
fix: add missing test comment for backend commenting standard (Task 2 review)
...
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com >
2026-07-02 14:57:55 +08:00
wangwei and Copilot
37ea27fcbe
feat: add TrackedLLMClient decorator for transparent usage recording
...
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com >
2026-07-02 14:49:06 +08:00
wangwei
74f327c85e
feat: add ModelUsageTracker for per-model token/connection tracking
2026-07-02 14:41:21 +08:00
wangwei
9212747e1b
update for 1. 优化 2.中英切换
2026-06-10 11:10:36 +08:00
wangwei
e7963b267e
fix somethings
2026-06-08 11:16:28 +08:00
ash66
3f69cad404
Fix SSE route dependency and align architecture docs
2026-05-18 16:32:42 +08:00
wangwei
10d04c4083
update
2026-05-14 15:07:34 +08:00
