Proven native-alias normalization landed; reported gateway case remains open
#3804 (0a4e4bc9bf) normalizes custom reasoning lists only for capability-backed canonical Codex-forward aliases. Arbitrary YYLJ gateway capability and the reported Desktop-version case remain unverified.
Verified against dev 5759d9ea2f1e7281cdc01eb9628f2e0a123fb59c. Original report by @leonclab. The attribution record was added in #3811.
Client or integration
Codex App
Area
Catalog / models
Summary
In the latest Codex Desktop runtime (0.153.4, Darwin arm64), the native binary strictly validates supported reasoning efforts for gpt-6-astra and only permits ['low', 'medium', 'high', 'xhigh', 'max']. Supplying minimal or none causes Codex to immediately reject the request before dispatch with:
Unsupported value: 'minimal' is not supported with the 'gpt-6-astra' model. Supported values are: 'low', 'medium', 'high', 'xhigh', and 'max'.
While OpenCodex logs [opencodex] Removed unsupported reasoning efforts: minimal, none, custom models mapped to Astra (e.g., forward proxy YYLJ/gpt-6-astra with legacy customModels[*].reasoningEfforts containing minimal or none) still have those unsupported efforts preserved in opencodex-catalog.json and turn execution contexts, triggering client-side rejection.
Reproduction
- Configure a custom model in
~/.opencodex/config.json pointing to an Astra upstream:
{
"provider": "YYLJ",
"modelId": "gpt-6-astra",
"reasoningEfforts": ["none", "minimal", "low", "medium", "high", "xhigh", "max"]
}
- Run
ocx sync.
- In Codex Desktop (version 0.153.4), start a turn or assign a subtask with reasoning effort
minimal.
- Observe the immediate 400 error:
{"type":"error","error":{"type":"invalid_request_error","code":"unsupported_value","message":"Unsupported value: 'minimal' is not supported with the 'gpt-6-astra' model. Supported values are: 'low', 'medium', 'high', 'xhigh', and 'max'.","param":"reasoning.effort"},"status":400}
Version
@bitkyc08/opencodex 2.43.0
Operating system
macOS 15.5 (Darwin arm64)
Provider and model
custom / gpt-6-astra
Logs or error output
[opencodex] Removed unsupported reasoning efforts: minimal, none
Unsupported value: 'minimal' is not supported with the 'gpt-6-astra' model. Supported values are: 'low', 'medium', 'high', 'xhigh', and 'max'.
Redacted configuration
{
"customModels": [
{
"provider": "YYLJ",
"modelId": "gpt-6-astra",
"reasoningEfforts": ["none", "minimal", "low", "medium", "high", "xhigh", "max"]
}
]
}
Checks
Proven native-alias normalization landed; reported gateway case remains open
#3804 (
0a4e4bc9bf) normalizes custom reasoning lists only for capability-backed canonical Codex-forward aliases. Arbitrary YYLJ gateway capability and the reported Desktop-version case remain unverified.Verified against dev
5759d9ea2f1e7281cdc01eb9628f2e0a123fb59c. Original report by @leonclab. The attribution record was added in #3811.Client or integration
Codex App
Area
Catalog / models
Summary
In the latest Codex Desktop runtime (0.153.4, Darwin arm64), the native binary strictly validates supported reasoning efforts for
gpt-6-astraand only permits['low', 'medium', 'high', 'xhigh', 'max']. Supplyingminimalornonecauses Codex to immediately reject the request before dispatch with:Unsupported value: 'minimal' is not supported with the 'gpt-6-astra' model. Supported values are: 'low', 'medium', 'high', 'xhigh', and 'max'.While OpenCodex logs
[opencodex] Removed unsupported reasoning efforts: minimal, none, custom models mapped to Astra (e.g., forward proxyYYLJ/gpt-6-astrawith legacycustomModels[*].reasoningEffortscontainingminimalornone) still have those unsupported efforts preserved inopencodex-catalog.jsonand turn execution contexts, triggering client-side rejection.Reproduction
~/.opencodex/config.jsonpointing to an Astra upstream:{ "provider": "YYLJ", "modelId": "gpt-6-astra", "reasoningEfforts": ["none", "minimal", "low", "medium", "high", "xhigh", "max"] }ocx sync.minimal.Version
@bitkyc08/opencodex 2.43.0
Operating system
macOS 15.5 (Darwin arm64)
Provider and model
custom / gpt-6-astra
Logs or error output
Redacted configuration
{ "customModels": [ { "provider": "YYLJ", "modelId": "gpt-6-astra", "reasoningEfforts": ["none", "minimal", "low", "medium", "high", "xhigh", "max"] } ] }Checks