wassname/moral-maps
1
0
Fork 0
mirror of https://github.com/wassname/moral-maps.git synced 2026-09-21 13:10:52 +08:00
Code Issues Packages Projects Releases Wiki Activity

Classify Nano failure as wrapper regression

Browse Source 
Co-Authored-By: PI[gpt-5.6-terra] <288921227+claudypoo@users.noreply.github.com>
This commit is contained in:
wassname
2026-09-17 10:13:53 +08:00
co-authored by PI[gpt-5.6-terra]
parent 7647874e75
commit 31db07780f
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
slop/audits/20260917_wvs_gpt5_nano_task_1622_mandatory_reasoning_failure.md
+1 -1
View File
@@ -32,7 +32,7 @@ The priority manifest required the cheapest new model to establish whether a 12
## Chronology and raw evidence
The saved catalog entry for `openai/gpt-5-nano` includes `reasoning`, `reasoning_effort`, and `structured_outputs` support. The task instead selected the prior optional-reasoning setting. The provider repeatedly returned:
The saved catalog entry for `openai/gpt-5-nano` includes `reasoning`, `reasoning_effort`, and `structured_outputs` support. The task instead selected the prior optional-reasoning setting. This is a wrapper/config regression, not a newly discovered mandatory-reasoning model-class issue: the ledger's Astra run `20260916T154406Z_95bb4d3939e9` used `reasoning: {"effort": "low"}` and strict schema, completed 144/144 samples with zero rescue starts, and recorded USD 0.69797. The provider repeatedly returned:
> `HTTP error for model openai/gpt-5-nano: {"error":{"message":"Reasoning is mandatory for this endpoint and cannot be disabled.","code":400,...}}`
>