redshift 01c01fe8ad fix: bill PPQ.AI BYOK upstream_inference_cost + BYOK fee ...

PPQ.AI (BYOK) requests were billed at ~5% of their true cost because
_resolve_usd_cost fell through to usage.cost (a small BYOK routing fee)
instead of using cost_details.upstream_inference_cost (the real inference
cost). The proxy operator absorbed the inference cost.

The fix adds a BYOK-specific branch in _resolve_usd_cost: when is_byok is
true and cost_details.upstream_inference_cost is present, bill
upstream_inference_cost + byok_fee — what PPQ actually deducts from the
balance. Non-BYOK providers (e.g. OpenRouter) are unaffected because their
usage.cost already equals upstream_inference_cost.

Regression tests mirror the live glm-5.2-fast request from GitHub issue #615,
asserting the corrected billing (940,274 msats vs the old 45,202 msats — a
20.8× undercharge).

Closes #615

2026-07-16 17:01:55 +08:00

..

integration

Merge pull request #578 from Routstr/token-error-code

2026-07-07 15:59:49 +02:00

unit

fix: bill PPQ.AI BYOK upstream_inference_cost + BYOK fee

2026-07-16 17:01:55 +08:00

run_integration.py

dump wip stash

2025-08-06 20:31:55 -03:00