Repository navigation
Commit 8e7e890
committed
test(codex): update cost expectations after reasoning token fix
Updated test expectations in daily-report.ts and monthly-report.ts to reflect
the corrected cost calculations after fixing the reasoning token double-counting
bug. The tests now expect the accurate cost values that exclude the erroneous
addition of reasoning_output_tokens to output_tokens.
Changes:
- Fixed expected cost calculation from 250 tokens to 200 tokens for gpt-5-mini output
- Added clarifying comments explaining the token breakdown for each model
- Ensures test accuracy with the corrected calculateCostUSD implementation
Test breakdown:
- gpt-5: 800 non-cached input @ $1.25/M, 200 cached @ $0.125/M, 500 output @ $10/M
- gpt-5-mini: 300 non-cached input @ $0.6/M, 100 cached @ $0.06/M, 200 output @ $2/M
(reasoning tokens already included in output count)
This change maintains test coverage while validating the accurate cost calculation
behavior after the reasoning token double-counting fix.1 parent 9b22b5b commit 8e7e890
2 files changed
Lines changed: 6 additions & 2 deletions
| Original file line number | Diff line number | Diff line change | |
|---|---|---|---|
| |||
163 | 163 | | |
164 | 164 | | |
165 | 165 | | |
| 166 | + | |
| 167 | + | |
166 | 168 | | |
167 | 169 | | |
168 | 170 | | |
169 | 171 | | |
170 | 172 | | |
171 | | - | |
| 173 | + | |
172 | 174 | | |
173 | 175 | | |
174 | 176 | | |
| |||
| Original file line number | Diff line number | Diff line change | |
|---|---|---|---|
| |||
170 | 170 | | |
171 | 171 | | |
172 | 172 | | |
| 173 | + | |
| 174 | + | |
173 | 175 | | |
174 | 176 | | |
175 | 177 | | |
176 | 178 | | |
177 | 179 | | |
178 | | - | |
| 180 | + | |
179 | 181 | | |
180 | 182 | | |
181 | 183 | | |
| |||
0 commit comments