[Lens] 'Total tokens' headline is dominated by re-counted cache-read; surface cache-read separately
Nobody has claimed this yet.
Assessment
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Newbie friendliness
- 57/100
- Issue type
- Feature
- Clarity
- Mostly clear
- Activity status
- Quiet
- Tech stack
- python
- Domain
- observability
Research direction
Start by reading the trace-detail header and the second bullet of #294, which is explicitly out of scope there; the issue does not name a file or test. Identify where the token totals are presented, then check that cache-read is shown separately from input and output, or that fresh tokens are distinguished from cached re-reads. Done when the headline no longer folds cache-read into an undifferentiated total, and any dollar figures respect plan-tier framing.
Written by the indexing model from the issue text.
Description
Follow-up from #294 (second bullet, deliberately out of scope there).
The trace-detail header (and token totals generally) sum cache-read tokens into a single "total tokens" figure. Because the cached prefix is re-read on every call, cache-read can be ~90%+ of the naive sum — so "total tokens" is dominated by re-counted cached context. It's technically real spend, but misleading as a headline "tokens" number.
Ask
Surface cache-read separately rather than folding it into one "total tokens" headline — e.g. break the header into input / output / cache-read / cache-write, or show "fresh tokens" vs "cached re-reads." Respect plan-tier framing on any dollar figures.
Not a blocker; cosmetic/clarity. Distinct from #294 (the parser over-count fix, now merged).
- Dominant language
- Python
- Stars
- 122
- Forks
- 35
- Avg merge
- 2d 16h
- Merged PRs (30d)
- 6
Getting set up
- Ships a Dockerfile or Docker Compose file
- Has a pull request template
- Read the contributing guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
More from Metabuilder-Labs/tokenjam
-
documentation
Difficulty 2/5 1-3 hours Newbie friendliness 85/100
Metabuilder-Labs/tokenjam#786 ·
-
enhancement good first issue help wanted
Difficulty 2/5 1-3 hours Newbie friendliness 78/100
Metabuilder-Labs/tokenjam#759 ·
-
bug
Difficulty 2/5 1-3 hours Newbie friendliness 72/100
Metabuilder-Labs/tokenjam#728 ·
-
bug help wanted
Difficulty 2/5 1-3 hours Newbie friendliness 85/100
Metabuilder-Labs/tokenjam#591 ·
-
bug good first issue help wanted
Difficulty 2/5 1-3 hours Newbie friendliness 82/100
Metabuilder-Labs/tokenjam#559 ·
All issues in Metabuilder-Labs/tokenjam
Similar issues
-
bug P1
Difficulty 2/5 1-3 hours Newbie friendliness 76/100
Toloka/tolokaforge#1947 ·
Maintainers usually reply within 1 day
-
SageMaker provider: streaming fails with NoStreamDataError on DJL Serving (LMI) endpointsPossibly taken @balajiaru claimed this today. Open
Difficulty 2/5 1-3 hours Newbie friendliness 88/100
UKGovernmentBEIS/inspect_ai#6127 ·
Maintainers usually reply within 2 days
-
Difficulty 2/5 1-3 hours Newbie friendliness 67/100
pydot/pydot#601 · 4 comments ·
Maintainers usually reply within 2 days
-
Difficulty 2/5 1-3 hours Newbie friendliness 68/100
letsencrypt/cp-cps#361 ·
-
Difficulty 2/5 1-3 hours Newbie friendliness 65/100