openai — failure-only retest
Comparison report · Transcript review
Index
Per-block counts
Latest retained results; all baseline labels were fail.
| Block |
Cases |
Pass / partial / fail / blocked / error |
| feedback |
1 |
1 / 0 / 0 / 0 / 0 |
| flow-selector |
1 |
1 / 0 / 0 / 0 / 0 |
| original-uat |
7 |
3 / 4 / 0 / 0 / 0 |
| regression |
5 |
5 / 0 / 0 / 0 / 0 |
| uat-additions |
4 |
1 / 0 / 3 / 0 / 0 |
| workflow-router |
1 |
1 / 0 / 0 / 0 / 0 |
Case transitions
| Block / case |
Round 1 |
Round 2 |
Round 3 |
Round 4 |
Latest evidence |
| feedback / F04 |
pass |
not rerun |
not rerun |
not rerun |
pass |
| flow-selector / W06 |
fail |
pass |
not rerun |
not rerun |
pass |
| original-uat / C01 |
partial |
not rerun |
not rerun |
not rerun |
partial |
| original-uat / C03 |
pass |
not rerun |
not rerun |
not rerun |
pass |
| original-uat / C24 |
partial |
not rerun |
not rerun |
not rerun |
partial |
| original-uat / C26 |
partial |
not rerun |
not rerun |
not rerun |
partial |
| original-uat / C78 |
fail |
fail |
blocked |
pass |
pass |
| original-uat / C81 |
fail |
pass |
not rerun |
not rerun |
pass |
| original-uat / C85 |
partial |
not rerun |
not rerun |
not rerun |
partial |
| regression / R01 |
fail |
fail |
pass |
not rerun |
pass |
| regression / R02 |
fail |
fail |
pass |
not rerun |
pass |
| regression / R07 |
fail |
fail |
error |
pass |
pass |
| regression / R14 |
pass |
not rerun |
not rerun |
not rerun |
pass |
| regression / R26 |
pass |
not rerun |
not rerun |
not rerun |
pass |
| uat-additions / C104 |
fail |
not rerun |
fail |
not rerun |
fail |
| uat-additions / C108 |
fail |
pass |
not rerun |
not rerun |
pass |
| uat-additions / C116 |
fail |
not rerun |
fail |
not rerun |
fail |
| uat-additions / C98 |
fail |
not rerun |
not rerun |
not rerun |
fail |
| workflow-router / W06 |
fail |
pass |
not rerun |
not rerun |
pass |