furyhawk/deer-flow
1
0
Fork 0
mirror of https://github.com/bytedance/deer-flow.git synced 2026-05-24 00:45:57 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat: show token usage per assistant response (#2270)

Browse Source 
* feat: show token usage per assistant response

* fix: align client models response with token usage

* fix: address token usage review feedback

* docs: clarify token usage config example

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
This commit is contained in:
YuJitang
2026-04-16 08:56:49 +08:00
committed by GitHub
parent 0e16a7fe55
commit 105db00987
17 changed files with 271 additions and 50 deletions
Download Patch File Download Diff File Expand all files Collapse all files
config.example.yaml
+4 -3
View File
@@ -21,10 +21,11 @@ config_version: 7
log_level: info
# ============================================================================
# Token Usage Tracking
# Token Usage
# ============================================================================
# Track LLM token usage per model call (input/output/total tokens)
# Logs at info level via TokenUsageMiddleware
# Enable token usage collection and display.
# When enabled, DeerFlow records input/output/total tokens per model call
# and shows usage metadata in the workspace UI when providers return it.
token_usage:
enabled: false