mirror of
https://github.com/openai/codex.git
synced 2026-05-01 03:42:05 +03:00
feat: expose provider capability bounds to app server clients (#20049)
follow up of #19442. The app server now exposes provider-derived bounds through a new v2 `modelProvider/read` method. The response reports the configured provider map key as `modelProvider` and returns the effective capability booleans so clients can align their UI with the same provider-owned limits used by core.
This commit is contained in:
5
codex-rs/app-server-protocol/schema/json/v2/ModelProviderCapabilitiesReadParams.json
generated
Normal file
5
codex-rs/app-server-protocol/schema/json/v2/ModelProviderCapabilitiesReadParams.json
generated
Normal file
@@ -0,0 +1,5 @@
|
||||
{
|
||||
"$schema": "http://json-schema.org/draft-07/schema#",
|
||||
"title": "ModelProviderCapabilitiesReadParams",
|
||||
"type": "object"
|
||||
}
|
||||
21
codex-rs/app-server-protocol/schema/json/v2/ModelProviderCapabilitiesReadResponse.json
generated
Normal file
21
codex-rs/app-server-protocol/schema/json/v2/ModelProviderCapabilitiesReadResponse.json
generated
Normal file
@@ -0,0 +1,21 @@
|
||||
{
|
||||
"$schema": "http://json-schema.org/draft-07/schema#",
|
||||
"properties": {
|
||||
"imageGeneration": {
|
||||
"type": "boolean"
|
||||
},
|
||||
"namespaceTools": {
|
||||
"type": "boolean"
|
||||
},
|
||||
"webSearch": {
|
||||
"type": "boolean"
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"imageGeneration",
|
||||
"namespaceTools",
|
||||
"webSearch"
|
||||
],
|
||||
"title": "ModelProviderCapabilitiesReadResponse",
|
||||
"type": "object"
|
||||
}
|
||||
Reference in New Issue
Block a user