AIRegulation/siemens_ragas
7
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(token-tracking): capture token usage in /api/score/async job runs

Browse Source 
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
This commit is contained in:
wangwei
2026-07-02 15:03:25 +08:00
co-authored by Copilot
parent 5494840431
commit 6a2bbf8239
3 changed files with 94 additions and 18 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/superpowers/plans/2026-07-02-token-usage-tracking.md
+4 -4
View File
@@ -1190,7 +1190,7 @@ def test_run_writes_token_usage_to_metadata(tmp_path, monkeypatch):
return {m: 0.9 for m in kwargs["metrics"]}
monkeypatch.setattr(
"webapp.services.score_job_manager.inline_scorer.score", _fake_score
"webapp.services.inline_scorer.inline_scorer.score", _fake_score
)
request = ScoreRequest(question="q?", answer="a.", metrics=["answer_relevancy"])
@@ -1216,7 +1216,7 @@ def test_run_writes_empty_token_usage_when_nothing_recorded(tmp_path, monkeypatc
return {m: 0.9 for m in kwargs["metrics"]}
monkeypatch.setattr(
"webapp.services.score_job_manager.inline_scorer.score", _fake_score
"webapp.services.inline_scorer.inline_scorer.score", _fake_score
)
request = ScoreRequest(question="q?", answer="a.", metrics=["answer_relevancy"])
@@ -1399,7 +1399,7 @@ def test_session_accumulates_token_usage_across_calls(tmp_path, monkeypatch):
return {m: 0.9 for m in kwargs["metrics"]}
monkeypatch.setattr(
"webapp.services.session_score_manager.inline_scorer.score", _fake_score
"webapp.services.inline_scorer.inline_scorer.score", _fake_score
)
request = ScoreRequest(question="q?", answer="a.", metrics=["answer_relevancy"])
@@ -1432,7 +1432,7 @@ def test_session_first_call_writes_token_usage_from_scratch(tmp_path, monkeypatc
return {m: 0.9 for m in kwargs["metrics"]}
monkeypatch.setattr(
"webapp.services.session_score_manager.inline_scorer.score", _fake_score
"webapp.services.inline_scorer.inline_scorer.score", _fake_score
)
request = ScoreRequest(question="q?", answer="a.", metrics=["answer_relevancy"])