Supervisor budget meter ignores PRICE_OVERRIDES_PER_1M
Maintainers usually reply within 1 day
Nobody has claimed this yet.
Assessment
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Newbie friendliness
- 68/100
Research direction
Locate the supervisor's per-scenario spend accounting and compare it with the export path in analysis.model_cost_latency. Trace how config.PRICE_OVERRIDES_PER_1M is applied when litellm provides no price, then verify that run_state.spent_usd, --budget-usd enforcement, and projections account for override-priced models.
Written by the indexing model from the issue text.
Description
During the gemini-3.6-flash run (2026-07-21) the supervisor's run_state spent_usd stayed 0.00 for the whole run: Gemini's API returns no cost field and litellm's price map does not cover the id, and the live meter does not fall back to config.PRICE_OVERRIDES_PER_1M the way export-time reconstruction (analysis.model_cost_latency) does. Consequence: the --budget-usd governor cannot bind for any model priced only by override, and projections read $0.
Fix: apply the same override fallback in the supervisor's per-scenario spend accounting that the export path uses.
🤖 Generated with Claude Code
- Dominant language
- Python
- Stars
- 2
- Forks
- 3
- Avg merge
- 11h 11m
- Merged PRs (30d)
- 22
Getting set up
- No Dockerfile or Docker Compose file
- No 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 PolicyEngine/policybench
-
v2 prompt and data: program-specific disability facts, integer inputs, and the take-up boundaryOpen
Difficulty 5/5 Over a week Newbie friendliness 38/100
PolicyEngine/policybench#165 · 2 comments ·
Maintainers usually reply within 1 day
-
Difficulty 5/5 Over a week Newbie friendliness 35/100
PolicyEngine/policybench#145 · 1 comment ·
Maintainers usually reply within 1 day
-
Difficulty 3/5 1-2 days Newbie friendliness 52/100
PolicyEngine/policybench#140 ·
Maintainers usually reply within 1 day
-
Difficulty 5/5 Over a week Newbie friendliness 25/100
PolicyEngine/policybench#139 · 2 comments ·
Maintainers usually reply within 1 day
-
Difficulty 5/5 Over a week Newbie friendliness 35/100
PolicyEngine/policybench#118 ·
Maintainers usually reply within 1 day
All issues in PolicyEngine/policybench
Similar issues
-
bug
Difficulty 2/5 1-3 hours Newbie friendliness 68/100
jbacalso24/mimry#291 ·
Maintainers usually reply within 1 day
-
good first issue
Difficulty 2/5 Under an hour Newbie friendliness 82/100
eli-alvarado/us-watchlist-alerts#14 ·
Maintainers usually reply within 1 day
-
from-review-extraction python severity:nit
Difficulty 2/5 1-3 hours Newbie friendliness 80/100
LearningCircuit/local-deep-research#7462 ·
Maintainers usually reply within 2 days
-
Difficulty 2/5 1-3 hours Newbie friendliness 82/100
cathrynlavery/diagram-design#441 ·
Maintainers usually reply within 2 days
-
[Cleanup] Include the public header in work_split.cppPossibly taken @blozano-tt claimed this today. Open
Difficulty 2/5 1-3 hours Newbie friendliness 82/100
tenstorrent/tt-metal#60850 ·
Maintainers usually reply within 1 day